人工智能学术速递[7.14]

访问www.arxivdaily.com获取含摘要速递，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域，更有搜索、收藏、发帖等功能！点击阅读原文即可访问

cs.AI人工智能，共计45篇

【1】 Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability 标题：RL中为什么难以泛化：认知POMDP与隐含部分可观测性

作者：Dibya Ghosh,Jad Rahme,Aviral Kumar,Amy Zhang,Ryan P. Adams,Sergey Levine 机构：UC Berkeley, Princeton University, Facebook AI Research 备注：First two authors contributed equally 链接：https://arxiv.org/abs/2107.06277 摘要：泛化是强化学习（RL）系统在现实世界中应用的核心挑战。在这篇文章中，我们证明了RL问题的序列结构需要新的方法来推广，而不仅仅是在监督学习中所使用的技术。虽然监督学习方法可以在不考虑认知不确定性的情况下有效地推广，但我们发现，也许令人惊讶的是，在RL中情况并非如此。我们证明，从有限的训练条件推广到不可见的测试条件，可以诱导内隐部分可观测性，有效地将完全观察到的mdp转化为pomdp。在此基础上，我们将RL中的泛化问题转化为求解诱导的部分观测Markov决策过程，我们称之为认知POMDP。我们证明了算法的失败模式，不适当地处理这个部分可观测性，并提出了一个简单的集成为基础的技术来近似解决部分观测问题。在Procgen基准测试套件上，我们证明了我们从认知POMDP导出的简单算法在推广上比现有方法有显著的提高。 摘要：Generalization is a central challenge for the deployment of reinforcement learning (RL) systems in the real world. In this paper, we show that the sequential structure of the RL problem necessitates new approaches to generalization beyond the well-studied techniques used in supervised learning. While supervised learning methods can generalize effectively without explicitly accounting for epistemic uncertainty, we show that, perhaps surprisingly, this is not the case in RL. We show that generalization to unseen test conditions from a limited number of training conditions induces implicit partial observability, effectively turning even fully-observed MDPs into POMDPs. Informed by this observation, we recast the problem of generalization in RL as solving the induced partially observed Markov decision process, which we call the epistemic POMDP. We demonstrate the failure modes of algorithms that do not appropriately handle this partial observability, and suggest a simple ensemble-based technique for approximately solving the partially observed problem. Empirically, we demonstrate that our simple algorithm derived from the epistemic POMDP achieves significant gains in generalization over current methods on the Procgen benchmark suite.

【2】 Fairness-aware Summarization for Justified Decision-Making 标题：合理决策的公平意识总结

作者：Moniba Keymanesh,Tanya Berger-Wolf,Micha Elsner,Srinivasan Parthasarathy 机构：The Ohio State University 备注：16 pages, 7 figures 链接：https://arxiv.org/abs/2107.06243 摘要：在累犯预测、设施检查、利益分配等许多应用中，个体了解与决策相关的信息对于模型的预测具有重要意义。此外，模型的预测应该是合理的。基本上，与决策相关的特征应为预测结果提供足够的信息，并应独立于种族和性别等受保护群体中的个人成员。在这项工作中，我们集中在（联合国）公平性的问题，在理由的文本为基础的神经模型。我们将模型的解释力与结果的公平性联系起来，并提出了一种公平感知的摘要机制来检测和抵消模型中的偏差。考虑到决策的自然语言解释可能存在偏差，我们使用多任务神经模型和基于综合梯度的归因机制，以摘要的形式提取高效用和无歧视的理由。然后，将提取的摘要用于训练模型，以便为个人做出决策。对几个真实数据集的结果表明，我们的方法：（i）帮助用户理解模型决策所使用的信息；（ii）提高结果的公平性，同时显著减少人口数据的泄露。 摘要：In many applications such as recidivism prediction, facility inspection, and benefit assignment, it's important for individuals to know the decision-relevant information for the model's prediction. In addition, the model's predictions should be fairly justified. Essentially, decision-relevant features should provide sufficient information for the predicted outcome and should be independent of the membership of individuals in protected groups such as race and gender. In this work, we focus on the problem of (un)fairness in the justification of the text-based neural models. We tie the explanatory power of the model to fairness in the outcome and propose a fairness-aware summarization mechanism to detect and counteract the bias in such models. Given a potentially biased natural language explanation for a decision, we use a multi-task neural model and an attribution mechanism based on integrated gradients to extract the high-utility and discrimination-free justifications in the form of a summary. The extracted summary is then used for training a model to make decisions for individuals. Results on several real-world datasets suggests that our method: (i) assists users to understand what information is used for the model's decision and (ii) enhances the fairness in outcomes while significantly reducing the demographic leakage.

【3】 Pessimistic Model-based Offline RL: PAC Bounds and Posterior Sampling under Partial Coverage 标题：基于悲观模型的离线RL：部分覆盖下的PAC界和后验抽样

作者：Masatoshi Uehara,Wen Sun 机构：Department of Computer Science, Cornell University 链接：https://arxiv.org/abs/2107.06226 摘要：研究了基于模型的离线强化学习。提出了一种基于约束悲观策略优化（CPPO）的算法，该算法利用了一个通用的函数类，并利用一个约束对悲观进行编码。在假设地面真值模型属于我们的函数类的情况下，CPPO可以只提供部分覆盖的离线数据进行学习，也就是说，相对于函数类的统计复杂度，它可以学习一个针对离线数据覆盖的任何策略完成的策略。然后我们证明了这个算法框架可以应用于许多特殊的马尔可夫决策过程，在这些过程中，附加的结构假设可以进一步完善部分覆盖的概念。一个显著的例子是具有表示学习的低秩MDP，其中部分覆盖是使用由潜在未知地面真值特征表示度量的相对条件数的概念来定义的。最后，介绍并研究了离线RL中的贝叶斯设置。贝叶斯离线RL的主要优点是，在算法上，我们不需要显式地构造悲观主义或奖惩，这可能很难超越线性结构的模型。提出了一种基于后验抽样的增量式策略优化算法（PS-PO），该算法从后验分布中对模型进行迭代抽样，并在抽样模型内进行一步增量式策略优化。理论上，在对先验分布的期望下，PS-PO可以在多项式样本复杂度的部分覆盖下学习一个近似最优策略。 摘要：We study model-based offline Reinforcement Learning with general function approximation. We present an algorithm named Constrained Pessimistic Policy Optimization (CPPO) which leverages a general function class and uses a constraint to encode pessimism. Under the assumption that the ground truth model belongs to our function class, CPPO can learn with the offline data only providing partial coverage, i.e., it can learn a policy that completes against any policy that is covered by the offline data, in polynomial sample complexity with respect to the statistical complexity of the function class. We then demonstrate that this algorithmic framework can be applied to many specialized Markov Decision Processes where the additional structural assumptions can further refine the concept of partial coverage. One notable example is low-rank MDP with representation learning where the partial coverage is defined using the concept of relative condition number measured by the underlying unknown ground truth feature representation. Finally, we introduce and study the Bayesian setting in offline RL. The key benefit of Bayesian offline RL is that algorithmically, we do not need to explicitly construct pessimism or reward penalty which could be hard beyond models with linear structures. We present a posterior sampling-based incremental policy optimization algorithm (PS-PO) which proceeds by iteratively sampling a model from the posterior distribution and performing one-step incremental policy optimization inside the sampled model. Theoretically, in expectation with respect to the prior distribution, PS-PO can learn a near optimal policy under partial coverage with polynomial sample complexity.

【4】 What classifiers know what they don't? 标题：什么样的分类员知道他们不知道的呢？

作者：Mohamed Ishmael Belghazi,David Lopez-Paz 机构：Facebook AI Research, Paris, France 备注：27 pages 链接：https://arxiv.org/abs/2107.06217 摘要：面对未知时的不确定性是智能决策的关键。然而，机器学习算法缺乏对其预测不确定性的可靠估计。这导致在训练中遇到看不见的课程时做出错误和过于自信的决定。尽管为分类器配备适合于现实世界的不确定性估计非常重要，但以前的工作主要集中在小数据集和训练数据与测试数据之间很少或没有类差异。为了弥补这一差距，我们引入UIMNET：一个真实的、ImageNet规模的测试平台，用于评估深度图像分类器的预测不确定性估计。我们的基准测试提供了八种最先进的算法、六种不确定性度量、四种域内度量、三种域外度量的实现，以及用于训练、校准、集成、选择和评估模型的全自动管道。我们的测试平台是开源的，所有的结果都可以从存储库中的固定提交中复制。添加新的数据集、算法、度量或度量只是几行代码的问题，因此希望UIMNET成为现实的、严格的和可复制的不确定性估计研究的垫脚石。我们的结果表明，ERM分类器的集合和单个MIMO分类器是目前测量域内和域外类的不确定性的两个最佳选择。 摘要：Being uncertain when facing the unknown is key to intelligent decision making. However, machine learning algorithms lack reliable estimates about their predictive uncertainty. This leads to wrong and overly-confident decisions when encountering classes unseen during training. Despite the importance of equipping classifiers with uncertainty estimates ready for the real world, prior work has focused on small datasets and little or no class discrepancy between training and testing data. To close this gap, we introduce UIMNET: a realistic, ImageNet-scale test-bed to evaluate predictive uncertainty estimates for deep image classifiers. Our benchmark provides implementations of eight state-of-the-art algorithms, six uncertainty measures, four in-domain metrics, three out-domain metrics, and a fully automated pipeline to train, calibrate, ensemble, select, and evaluate models. Our test-bed is open-source and all of our results are reproducible from a fixed commit in our repository. Adding new datasets, algorithms, measures, or metrics is a matter of a few lines of code-in so hoping that UIMNET becomes a stepping stone towards realistic, rigorous, and reproducible research in uncertainty estimation. Our results show that ensembles of ERM classifiers as well as single MIMO classifiers are the two best alternatives currently available to measure uncertainty about both in-domain and out-domain classes.

【5】 'CADSketchNet' -- An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks 标题：CADSketchNet--一种用于深度神经网络三维CAD模型检索的注释草图数据集

作者：Bharadwaj Manda,Shubham Dhayarkar,Sai Mitheran,V. K. Viekash,Ramanathan Muthuganapathy 机构： Indian Institute of Technology Madras , National Institute of Technology Tiruchirappalli 备注：Computers & Graphics Journal, Special Section on 3DOR 2021 链接：https://arxiv.org/abs/2107.06212 摘要：三维建模和数字存档领域的不断进步导致了数字存储数据量的激增。因此，根据存储在这些数据库中的数据类型，开发了若干检索系统。然而，与文本数据或图像不同的是，执行三维模型搜索是非常重要的。在三维模型中，由于存在孔、体积特征、锐边等，检索三维工程/CAD模型或机械部件更具挑战性，这使得CAD本身成为一个领域。本文的研究工作旨在开发一个适合于建立基于深度学习的三维CAD模型检索系统的数据集。从可用的CAD数据库中收集3D CAD模型，并准备计算机生成的草图数据集，称为“CADSketchNet”。此外，零部件的手绘草图也添加到CADSetchNet中。利用该数据集的草图图像，本文还旨在评估各种检索系统或接受草图图像作为输入查询的三维CAD模型搜索引擎的性能。在CADSketchNet上构建并测试了多个实验模型。这些实验，连同模型架构，相似性度量的选择与搜索结果一起被报告。 摘要：Ongoing advancements in the fields of 3D modelling and digital archiving have led to an outburst in the amount of data stored digitally. Consequently, several retrieval systems have been developed depending on the type of data stored in these databases. However, unlike text data or images, performing a search for 3D models is non-trivial. Among 3D models, retrieving 3D Engineering/CAD models or mechanical components is even more challenging due to the presence of holes, volumetric features, presence of sharp edges etc., which make CAD a domain unto itself. The research work presented in this paper aims at developing a dataset suitable for building a retrieval system for 3D CAD models based on deep learning. 3D CAD models from the available CAD databases are collected, and a dataset of computer-generated sketch data, termed 'CADSketchNet', has been prepared. Additionally, hand-drawn sketches of the components are also added to CADSketchNet. Using the sketch images from this dataset, the paper also aims at evaluating the performance of various retrieval system or a search engine for 3D CAD models that accepts a sketch image as the input query. Many experimental models are constructed and tested on CADSketchNet. These experiments, along with the model architecture, choice of similarity metrics are reported along with the search results.

【6】 Correlation Analysis between the Robustness of Sparse Neural Networks and their Random Hidden Structural Priors 标题：稀疏神经网络的鲁棒性与其随机隐含结构先验的相关分析

作者：M. Ben Amor,J. Stier,M. Granitzer 机构：deUniversity of PassauABSTRACTDeep learning models have been shown to be vulnerable to adversarial attacks 链接：https://arxiv.org/abs/2107.06158 摘要：深度学习模式已被证明易受对手攻击。这种认知导致了对深度学习模型的分析，不仅从其性能指标的角度，而且从其对某些类型的对抗性攻击的鲁棒性的角度。我们从图论的角度将神经网络的体系结构与它们的健壮性联系起来，又向前迈出了一步。我们的目的是研究稀疏神经网络的图论性质和鲁棒性之间存在的任何相关性。我们的假设是，作为神经网络结构先验的图论性质与其鲁棒性有关。为了回答这一假设，我们设计了一个实证研究，通过随机图获得的神经网络模型作为网络的稀疏结构先验。我们还研究了一个随机剪枝的完全连接网络作为参考点的评估。我们发现，鲁棒性度量与初始化方法无关，但与图的性质表现出弱相关性：图的密度越高，鲁棒性越低；而平均路径长度和平均节点偏心率越高，鲁棒性度量则表现出负相关性。我们希望激励进一步的实证和分析研究，以加紧回答我们的假设。 摘要：Deep learning models have been shown to be vulnerable to adversarial attacks. This perception led to analyzing deep learning models not only from the perspective of their performance measures but also their robustness to certain types of adversarial attacks. We take another step forward in relating the architectural structure of neural networks from a graph theoretic perspective to their robustness. We aim to investigate any existing correlations between graph theoretic properties and the robustness of Sparse Neural Networks. Our hypothesis is, that graph theoretic properties as a prior of neural network structures are related to their robustness. To answer to this hypothesis, we designed an empirical study with neural network models obtained through random graphs used as sparse structural priors for the networks. We additionally investigated the evaluation of a randomly pruned fully connected network as a point of reference. We found that robustness measures are independent of initialization methods but show weak correlations with graph properties: higher graph densities correlate with lower robustness, but higher average path lengths and average node eccentricities show negative correlations with robustness measures. We hope to motivate further empirical and analytical research to tightening an answer to our hypothesis.

【7】 Ontology-Based Process Modelling -- Will we live to see it? 标题：基于本体的流程建模--我们能活着看到它吗？

作者：Carl Corea,Michael Fellmann,Patrick Delfmann 机构： University of Koblenz-Landau, Germany, University of Rostock, Germany 链接：https://arxiv.org/abs/2107.06146 摘要：从理论上讲，基于本体的流程建模（OBPM）在扩展业务流程管理方面具有巨大的潜力。许多工作已经研究了OBPM，并明确了潜在的便利条件，如消除歧义或支持对公司流程的高级推理。然而，尽管这在学术界得到了认可，但广泛的行业采用仍然不见踪影。这主要归因于这样一个事实，即最初创建本体和流程模型注释仍然需要大量的手工劳动。只要这些问题没有得到解决，实施OBPM在实践中就显得不可行。因此，在这项工作中，我们确定了成功实施OBPM所需的需求，并评估了这些需求的研究现状。我们的研究结果表明，促进OBPM的方法的研究进展仍然很低，迫切需要扩展现有的方法。 摘要：In theory, ontology-based process modelling (OBPM) bares great potential to extend business process management. Many works have studied OBPM and are clear on the potential amenities, such as eliminating ambiguities or enabling advanced reasoning over company processes. However, despite this approval in academia, a widespread industry adoption is still nowhere to be seen. This can be mainly attributed to the fact, that it still requires high amounts of manual labour to initially create ontologies and annotations to process models. As long as these problems are not addressed, implementing OBPM seems unfeasible in practice. In this work, we therefore identify requirements needed for a successful implementation of OBPM and assess the current state of research w.r.t. these requirements. Our results indicate that the research progress for means to facilitate OBPM are still alarmingly low and there needs to be urgent work on extending existing approaches.

【8】 Deep learning approaches to Earth Observation change detection 标题：深度学习方法在对地观测变化检测中的应用

作者：Antonio Di Pilato,Nicolò Taggio,Alexis Pompili,Michele Iacobellis,Adriano Di Florio,Davide Passarelli,Sergio Samarelli 机构：Dipartimento Interateneo di Fisica, Università degli Studi di Bari, Bari, Italy, Planetek Italia, Politecnico di Bari 链接：https://arxiv.org/abs/2107.06132 摘要：在过去的几年里，人们对遥感领域中的变化检测越来越感兴趣。搜索卫星图像的变化有许多有用的应用，从土地覆盖和土地利用分析到异常检测。特别是，通过多年的观测，城市变化检测为研究城市蔓延和发展提供了一个有效的工具。同时，变化检测往往是一项具有计算挑战性和耗时的任务，这就需要创新的方法来保证在合理的时间内以无可置疑的价值获得最佳结果。在本文中，我们提出了两种不同的变化检测方法（语义分割和分类），这两种方法都利用卷积神经网络来获得良好的结果，可以进一步细化并用于各种应用的后处理工作流。 摘要：The interest for change detection in the field of remote sensing has increased in the last few years. Searching for changes in satellite images has many useful applications, ranging from land cover and land use analysis to anomaly detection. In particular, urban change detection provides an efficient tool to study urban spread and growth through several years of observation. At the same time, change detection is often a computationally challenging and time-consuming task, which requires innovative methods to guarantee optimal results with unquestionable value and within reasonable time. In this paper we present two different approaches to change detection (semantic segmentation and classification) that both exploit convolutional neural networks to achieve good results, which can be further refined and used in a post-processing workflow for a large variety of applications.

【9】 A New Approach for Semantic Web Matching 标题：一种新的语义网匹配方法

作者：Kamran Zamanifar,Golsa Heidari,Naser Nematbakhsh,Farhad Mardookhi 机构： Dept. of Computer Science, University of Isfahan, Isfahan, Iran, Young Researchers Club, Computer Engineering Department, Islamic Azad University, Najafabad Branch, Iran 备注：9 pages, 6 figures, SUComS 2010 链接：https://arxiv.org/abs/2107.06083 摘要：本文提出了一种新的语义web匹配方法来提高web服务替换的性能。因为在自动化系统中，我们应该确保自我修复、自我配置、自我优化和自我管理，所有服务都应该始终可用，如果其中一个服务崩溃，应该用最相似的服务替换。候选服务以通用描述、发现和集成（universaldescription，Discovery and Integration，UDDI）的形式发布，所有这些服务都使用Web本体语言（OWL）。利用二部图对崩溃服务和候选服务进行匹配。然后我们选择了最好的服务，匹配率最高。事实上，我们比较了两个服务的功能和能力，看看它们有多匹配。我们发现匹配两个web服务的最佳方法是比较它们的功能。 摘要：In this work we propose a new approach for semantic web matching to improve the performance of Web Service replacement. Because in automatic systems we should ensure the self-healing, self-configuration, self-optimization and self-management, all services should be always available and if one of them crashes, it should be replaced with the most similar one. Candidate services are advertised in Universal Description, Discovery and Integration (UDDI) all in Web Ontology Language (OWL). By the help of bipartite graph, we did the matching between the crashed service and a Candidate one. Then we chose the best service, which had the maximum rate of matching. In fact we compare two services` functionalities and capabilities to see how much they match. We found that the best way for matching two web services, is comparing the functionalities of them.

【10】 A Rational Entailment for Expressive Description Logics via Description Logic Programs 标题：基于描述逻辑程序的表达描述逻辑的理性蕴涵

作者：Giovanni Casini,Umberto Straccia 链接：https://arxiv.org/abs/2107.06075 摘要：Lehmann和Magidor的有理闭包被认为是非单调逻辑领域的一个里程碑，它也在描述逻辑中被重新表述。我们在这里展示了如何为表达型DLs（如SROIQ）建模合理的蕴涵形式，提供了一种新的推理过程，将非单调的DL知识库编译成描述逻辑程序（DL程序）。 摘要：Lehmann and Magidor's rational closure is acknowledged as a landmark in the field of non-monotonic logics and it has also been re-formulated in the context of Description Logics (DLs). We show here how to model a rational form of entailment for expressive DLs, such as SROIQ, providing a novel reasoning procedure that compiles a non-monotone DL knowledge base into a description logic program (dl-program).

【11】 aiSTROM -- A roadmap for developing a successful AI strategy 标题：aiSTROM--开发成功的人工智能战略的路线图

作者：Dorien Herremans 机构：Singapore University of Technology and Design 链接：https://arxiv.org/abs/2107.06071 摘要：Rackspace Technology最近对1870家公司进行的一项调查显示，共有34%的人工智能研发项目失败或被放弃。我们提出了一个新的战略框架，aiSTROM，使管理者能够创建一个成功的人工智能战略的基础上彻底的文献回顾。这提供了一种独特的集成方法，可以指导管理者和开发人员解决实现过程中的各种挑战。在aiSTROM框架中，我们首先确定前n个潜在项目（通常为3-5个）。对于其中每一个领域，都对七个重点领域进行了透彻的分析。这些领域包括创建一个数据策略，该策略考虑到独特的跨部门机器学习数据要求、安全性和法律要求。在人工智能人才匮乏的情况下，aiSTROM指导管理者思考如何组建一个跨学科的人工智能（AI）实施团队。一旦AI团队战略建立起来，就需要在组织内部进行定位，可以跨部门，也可以作为一个单独的部门。其他考虑因素包括人工智能即服务（AIaas）或外包开发。着眼于新技术，我们必须考虑诸如偏见、黑箱模型的合法性以及让人处于循环中的挑战。接下来，与任何项目一样，我们需要基于价值的关键绩效指标（kpi）来跟踪和验证进度。根据公司的风险战略，SWOT分析（优势、劣势、机会和威胁）有助于进一步对入围项目进行分类。最后，我们应该确保我们的战略包括对员工的继续教育，以形成一种收养文化。这个独特而全面的框架为管理者和主要开发人员提供了一个有价值的、文献支持的工具。 摘要：A total of 34% of AI research and development projects fails or are abandoned, according to a recent survey by Rackspace Technology of 1,870 companies. We propose a new strategic framework, aiSTROM, that empowers managers to create a successful AI strategy based on a thorough literature review. This provides a unique and integrated approach that guides managers and lead developers through the various challenges in the implementation process. In the aiSTROM framework, we start by identifying the top n potential projects (typically 3-5). For each of those, seven areas of focus are thoroughly analysed. These areas include creating a data strategy that takes into account unique cross-departmental machine learning data requirements, security, and legal requirements. aiSTROM then guides managers to think about how to put together an interdisciplinary artificial intelligence (AI) implementation team given the scarcity of AI talent. Once an AI team strategy has been established, it needs to be positioned within the organization, either cross-departmental or as a separate division. Other considerations include AI as a service (AIaas), or outsourcing development. Looking at new technologies, we have to consider challenges such as bias, legality of black-box-models, and keeping humans in the loop. Next, like any project, we need value-based key performance indicators (KPIs) to track and validate the progress. Depending on the company's risk-strategy, a SWOT analysis (strengths, weaknesses, opportunities, and threats) can help further classify the shortlisted projects. Finally, we should make sure that our strategy includes continuous education of employees to enable a culture of adoption. This unique and comprehensive framework offers a valuable, literature supported, tool for managers and lead developers.

【12】 Pattern Discovery and Validation Using Scientific Research Methods 标题：基于科学研究方法的模式发现与验证

作者：Dirk Riehle,Nikolay Harutyunyan,Ann Barcomb 机构：Friedrich-Alexander-University, Erlangen-Nürnberg, University of Calgary 链接：https://arxiv.org/abs/2107.06065 摘要：模式发现，即发现先前未识别的模式的过程，通常作为一个临时过程来执行，所提出的模式的质量几乎没有确定性。模式验证，即验证所提出的模式的准确性的过程，仍然由简单的“三个规则”的启发式方法控制。本文展示了如何使用已建立的科学研究方法进行模式发现和验证。我们提出了一种具体的方法，称为手册方法，它使用定性调查、行动研究和案例研究来发现和评估模式，并讨论了一般使用科学方法的基本原则。我们使用三个探索性研究来评估手册方法，并证明其有效性。 摘要：Pattern discovery, the process of discovering previously unrecognized patterns, is often performed as an ad-hoc process with little resulting certainty in the quality of the proposed patterns. Pattern validation, the process of validating the accuracy of proposed patterns, remains dominated by the simple heuristic of "the rule of three". This article shows how to use established scientific research methods for the purpose of pattern discovery and validation. We present a specific approach, called the handbook method, that uses the qualitative survey, action research, and case study research for pattern discovery and evaluation, and we discuss the underlying principle of using scientific methods in general. We evaluate the handbook method using three exploratory studies and demonstrate its usefulness.

【13】 Indian Legal NLP Benchmarks : A Survey 标题：印度法律NLP基准：一项调查

作者：Prathamesh Kalamkar,Janani Venugopalan Ph. D.,Vivek Raghavan Ph. D 机构：ThoughtWorks, Joint first author, Janani Venugopalan, Vivek Raghavan, This work is funded by EkStep 链接：https://arxiv.org/abs/2107.06056 摘要：提供具有挑战性的基准是AI在特定领域发展的关键。由于法律文本与普通英语文本有很大不同，因此需要为印度法律文本创建单独的自然语言处理基准，这些基准具有挑战性，并侧重于特定于法律制度的任务。这将刺激印度法律文本自然语言处理应用的创新，并将有利于人工智能社区和法律界。我们回顾了这一领域的现有工作，并提出了为印度法律自然语言处理创建新基准的想法。 摘要：Availability of challenging benchmarks is the key to advancement of AI in a specific field.Since Legal Text is significantly different than normal English text, there is a need to create separate Natural Language Processing benchmarks for Indian Legal Text which are challenging and focus on tasks specific to Legal Systems. This will spur innovation in applications of Natural language Processing for Indian Legal Text and will benefit AI community and Legal fraternity. We review the existing work in this area and propose ideas to create new benchmarks for Indian Legal Natural Language Processing.

【14】 Parallelisable Existential Rules: a Story of Pieces 标题：可并行存在规则：片断的故事

作者：Maxime Buron,Marie-Laure Mugnier,Michaël Thomazo 机构： University of Oxford, United Kingdom, LIRMM, Inria, University of Montpellier, CNRS, France, Inria, DI ENS, ENS, CNRS, PSL University & Inria, France 链接：https://arxiv.org/abs/2107.06054 摘要：在本文中，我们考虑存在规则，表现形式主义非常适合于本体论知识和数据的代表性的本体映射的背景下，基于本体的数据集成。chase是使用存在规则进行推理的基本工具，因为它从数据库实例计算规则所包含的所有事实。我们引入了可并行的存在规则集，对于这些存在规则集，追逐可以从任何实例开始，在单个宽度的第一步中进行计算。我们研究的问题是这些规则集的特征。我们证明了可并行规则集正是那些既有界又属于一类新规则的规则集，称为分段规则。分段类特别包括边防存在规则和（普通）数据日志。我们还给出了可并行规则集的另一个特征，即基于重写的规则组合。 摘要：In this paper, we consider existential rules, an expressive formalism well suited to the representation of ontological knowledge and data-to-ontology mappings in the context of ontology-based data integration. The chase is a fundamental tool to do reasoning with existential rules as it computes all the facts entailed by the rules from a database instance. We introduce parallelisable sets of existential rules, for which the chase can be computed in a single breadth-first step from any instance. The question we investigate is the characterization of such rule sets. We show that parallelisable rule sets are exactly those rule sets both bounded for the chase and belonging to a novel class of rules, called pieceful. The pieceful class includes in particular frontier-guarded existential rules and (plain) datalog. We also give another characterization of parallelisable rule sets in terms of rule composition based on rewriting.

【15】 A Graph Data Augmentation Strategy with Entropy Preserving 标题：一种保熵的图形数据增强策略

作者：Xue Liu,Dan Sun,Wei Wei 机构：Beijing System Design Institute of Electro-Mechanic Engineering, Beijing, China, School of Mathematical Sciences, Beihang University, Beijing, China, Key Laboratory of Mathematics, Informatics and Behavioral Semantics, Ministry of Education, China 链接：https://arxiv.org/abs/2107.06048 摘要：Kipf和Welling提出的图卷积网络（GCNs）是半监督学习的有效模型，但面临着过度平滑的障碍，这将削弱GCNs的表示能力。近年来，一些研究者提出了通过随机扰动图的拓扑结构或特征矩阵来生成数据增强作为训练的输入。然而，这些操作都要付出信息结构完整性破坏的代价，不可避免地牺牲原始图中的信息。本文提出了一种新的图熵定义，作为评价图中特征信息扩散的定量指标。在保持图熵的前提下，提出了一种在保证图拓扑完整性的前提下，利用随机机制生成扰动训练数据的有效策略。在真实数据集上进行了大量的实验，结果表明，与基线激增相比，本文提出的方法在提高半监督节点分类精度方面是有效的。除此之外，我们提出的方法在训练过程中显著提高了GCNs的鲁棒性和泛化能力。 摘要：The Graph Convolutional Networks (GCNs) proposed by Kipf and Welling are effective models for semi-supervised learning, but facing the obstacle of over-smoothing, which will weaken the representation ability of GCNs. Recently some works are proposed to tackle with above limitation by randomly perturbing graph topology or feature matrix to generate data augmentations as input for training. However, these operations have to pay the price of information structure integrity breaking, and inevitably sacrifice information stochastically from original graph. In this paper, we introduce a novel graph entropy definition as an quantitative index to evaluate feature information diffusion among a graph. Under considerations of preserving graph entropy, we propose an effective strategy to generate perturbed training data using a stochastic mechanism but guaranteeing graph topology integrity and with only a small amount of graph entropy decaying. Extensive experiments have been conducted on real-world datasets and the results verify the effectiveness of our proposed method in improving semi-supervised node classification accuracy compared with a surge of baselines. Beyond that, our proposed approach significantly enhances the robustness and generalization ability of GCNs during the training process.

【16】 Understanding Factors Affecting Fuel Consumption of Vehicles Through Explainable AI: A Use Case With Explainable Boosting Machines 标题：通过可解释人工智能理解影响车辆油耗的因素：使用可解释助推器的用例

作者：Alberto Barbado,Óscar Corcho 机构：|, Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, Boadilla del Monte, Spain, Correspondence, Email:, Present address, Telefónica, Madrid, Spain, Funding information 备注：29 pages, 15 Figures 链接：https://arxiv.org/abs/2107.06031 摘要：对于许多使用车队运营的公司来说，一个重要的经济成本与其燃油消耗有关。这种消耗可以通过在某些方面采取行动来减少，例如车辆驾驶员的驾驶行为方式。改善驾驶行为（和其他特性）可以节省车队的燃油，而无需改变其他方面，如计划的路线或站点。这不仅对于降低公司内部的经济成本非常重要，而且对于减少与燃油消耗相关的排放也非常重要，主要是当车辆配备汽油或柴油发动机时。在本文中，我们展示了如何解释人工智能（XAI）可以用于量化不同特征组对特定车队燃油消耗的影响。为此，我们使用可解释的助推器（EBM）对不同的特征（最多70个）进行训练，以便首先对它们和燃油消耗之间的关系进行建模，然后对其进行解释。在此基础上，我们将EBM提供的解释与文献中估计这些特性可能对燃油消耗量产生的潜在影响的一般参考文献进行了比较，以验证这种方法。我们使用几个真实世界的行业数据集来表示不同类型的车队，从有乘用车的车队到包括卡车等重型车辆的车队。 摘要：A significant economic cost for many companies that operate with fleets of vehicles is related to their fuel consumption. This consumption can be reduced by acting over some aspects, such as the driving behaviour style of vehicle drivers. Improving driving behaviour (and other features) can save fuel on a fleet of vehicles without needing to change other aspects, such as the planned routes or stops. This is important not only for mitigating economic costs within a company, but also for reducing the emissions associated to fuel consumption, mainly when the vehicles have petrol or diesel engines. In this paper we show how Explainable Artificial Intelligence (XAI) can be useful for quantifying the impact that different feature groups have on the fuel consumption of a particular fleet. For that, we use Explainable Boosting Machines (EBM) that are trained over different features (up to 70) in order to first model the relationship between them and the fuel consumption, and then explain it. With it, we compare the explanations provided by the EBM with general references from the literature that estimate the potential impact that those features may have on the fuel consumption, in order to validate this approach. We work with several real-world industry datasets that represent different types of fleets, from ones that have passenger cars to others that include heavy-duty vehicles such as trucks.

【17】 This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces 标题：这个人(可能)是存在的。针对GAN生成的人脸的身份成员身份攻击

作者：Ryan Webster,Julien Rabin,Loic Simon,Frederic Jurie 机构： University of Caen Normandie, ENSI Caen 链接：https://arxiv.org/abs/2107.06018 摘要：最近，生成性对抗网络（GANs）实现了惊人的现实主义，甚至愚弄了人类的观察者。事实上，流行的舌战网站{\small\url{http://thispersondoesnotexist.com}}，用甘生成的图片嘲讽用户，这些图片看起来太真实了，让人难以置信。另一方面，GANs确实泄露了他们训练数据的信息，最近文献中显示的成员攻击就是明证。在这项工作中，我们通过构建一个成功的新的成员攻击，挑战了甘面临的假设，即真的是新的创作。与以前的工作不同，我们的攻击可以准确地识别与训练样本具有相同身份的样本，而不是相同的样本。我们通过几个流行的人脸数据集和GAN训练程序展示了我们的攻击兴趣。值得注意的是，我们发现，即使存在显著的数据集多样性，一个过度代表的人也会引起隐私问题。 摘要：Recently, generative adversarial networks (GANs) have achieved stunning realism, fooling even human observers. Indeed, the popular tongue-in-cheek website {\small \url{ http://thispersondoesnotexist.com}}, taunts users with GAN generated images that seem too real to believe. On the other hand, GANs do leak information about their training data, as evidenced by membership attacks recently demonstrated in the literature. In this work, we challenge the assumption that GAN faces really are novel creations, by constructing a successful membership attack of a new kind. Unlike previous works, our attack can accurately discern samples sharing the same identity as training samples without being the same samples. We demonstrate the interest of our attack across several popular face datasets and GAN training procedures. Notably, we show that even in the presence of significant dataset diversity, an over represented person can pose a privacy concern.

【18】 A Classification of Artificial Intelligence Systems for Mathematics Education 标题：面向数学教育的人工智能系统分类

作者：Steven Van Vaerenbergh,Adrián Pérez-Suay 机构： Universidad de Cantabria, Universitat de València 备注：Chapter in the upcoming book "Mathematics Education in the Age of Artificial Intelligence: How Artificial Intelligence can serve Mathematical Human Learning", Springer Nature, edited by P.R. Richard, P. V\'elez, and S. Van Vaerenbergh 链接：https://arxiv.org/abs/2107.06015 摘要：这一章提供了不同的人工智能（AI）系统的概述，这些系统正被用于当代数学教育（ME）的数字工具中。它针对的是人工智能和机器学习（ML）领域的研究人员，我们为他们阐明了在教育应用中使用的特定技术；在我的研究人员身上，我们为他们澄清：i）当前人工智能技术的可能性是什么，ii）什么仍然遥不可及，以及iii）在不久的将来会发生什么。我们通过建立一个高级的人工智能工具分类法开始我们的分析，这些人工智能工具作为数字ME应用程序中的组件。然后，我们详细描述了这些人工智能工具，特别是ML，是如何在两个关键应用中使用的，特别是基于人工智能的计算器和智能教学系统。本章最后讨论了学生建模系统及其与人工智能的关系。 摘要：This chapter provides an overview of the different Artificial Intelligence (AI) systems that are being used in contemporary digital tools for Mathematics Education (ME). It is aimed at researchers in AI and Machine Learning (ML), for whom we shed some light on the specific technologies that are being used in educational applications; and at researchers in ME, for whom we clarify: i) what the possibilities of the current AI technologies are, ii) what is still out of reach and iii) what is to be expected in the near future. We start our analysis by establishing a high-level taxonomy of AI tools that are found as components in digital ME applications. Then, we describe in detail how these AI tools, and in particular ML, are being used in two key applications, specifically AI-based calculators and intelligent tutoring systems. We finish the chapter with a discussion about student modeling systems and their relationship to artificial general intelligence.

【19】 Identifying Influential Users in Unknown Social Networks for Adaptive Incentive Allocation Under Budget Restriction 标题：预算约束下自适应激励分配的未知社会网络中有影响力用户识别

作者：Shiqing Wu,Weihua Li,Hao Shen,Quan Bai 机构：University of Tasmania, Australia, Auckland University of Technology, New Zealand, cfortiss GmbH, Forschungsinstitut des Freistaats Bayern, Germany 链接：https://arxiv.org/abs/2107.05992 摘要：近年来，推荐系统在许多领域得到了广泛的应用。这些系统无法影响用户选择系统期望的行为。同时，提供激励已被证明是影响用户行为的一种更主动的方式。由于预算限制，可以激励的用户数量受到限制。基于此，我们打算利用用户之间存在的社会影响力来增强激励效果。通过直接激励有影响力的用户，他们在社交网络中的追随者可能受到间接激励。然而，在许多现实场景中，网络的拓扑结构通常是未知的，这使得识别有影响力的用户变得困难。为了解决上述问题，本文提出了一种在未知网络中挖掘有影响用户的新算法，该算法可以在不知道网络拓扑的情况下，根据用户的历史行为来估计用户之间的影响关系。同时，设计了一种基于用户偏好和影响能力的自适应激励分配方法。我们通过在合成数据集和真实数据集上进行实验来评估所提方法的性能。实验结果证明了所提方法的有效性。 摘要：In recent years, recommendation systems have been widely applied in many domains. These systems are impotent in affecting users to choose the behavior that the system expects. Meanwhile, providing incentives has been proven to be a more proactive way to affect users' behaviors. Due to the budget limitation, the number of users who can be incentivized is restricted. In this light, we intend to utilize social influence existing among users to enhance the effect of incentivization. Through incentivizing influential users directly, their followers in the social network are possibly incentivized indirectly. However, in many real-world scenarios, the topological structure of the network is usually unknown, which makes identifying influential users difficult. To tackle the aforementioned challenges, in this paper, we propose a novel algorithm for exploring influential users in unknown networks, which can estimate the influential relationships among users based on their historical behaviors and without knowing the topology of the network. Meanwhile, we design an adaptive incentive allocation approach that determines incentive values based on users' preferences and their influence ability. We evaluate the performance of the proposed approaches by conducting experiments on both synthetic and real-world datasets. The experimental results demonstrate the effectiveness of the proposed approaches.

【20】 DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement 标题：神性：数据可视化和模型精细化的各种有影响力的训练要点

作者：Umang Bhatt,Isabel Chien,Muhammad Bilal Zafar,Adrian Weller 机构：Amazon AWS AI, University of Cambridge & The Alan Turing Institute 备注：30 pages, 32 figures 链接：https://arxiv.org/abs/2107.05978 摘要：随着机器学习（ML）模型复杂性的增加，导致模型缺乏预测的可解释性，人们已经开发了几种方法来根据对模型影响最大的训练数据点来解释模型的行为。然而，这些方法倾向于将异常值标记为具有高度影响力的点，从而限制了从业者从不代表训练数据的点中得出的见解。在这项工作中，我们朝着寻找有影响力的训练点迈出了一步，这些训练点也很好地代表了训练数据。我们首先回顾了为训练点分配重要性分数的方法。基于重要性得分，我们提出了一种方法来选择一组不同的有影响力的（神圣的）训练点作为模型行为的有用解释。由于实践者可能不仅对发现对模型准确性有影响的数据点感兴趣，而且对其他重要指标也感兴趣，因此我们将展示如何在组公平性的基础上评估训练数据点。我们的方法可以识别导致不公平的训练点，去除这些训练点可以提高训练的公平性。我们的定量实验和用户研究表明，与早期的方法相比，可视化神圣点有助于从业者更好地理解和解释模型行为。 摘要：As the complexity of machine learning (ML) models increases, resulting in a lack of prediction explainability, several methods have been developed to explain a model's behavior in terms of the training data points that most influence the model. However, these methods tend to mark outliers as highly influential points, limiting the insights that practitioners can draw from points that are not representative of the training data. In this work, we take a step towards finding influential training points that also represent the training data well. We first review methods for assigning importance scores to training points. Given importance scores, we propose a method to select a set of DIVerse INfluEntial (DIVINE) training points as a useful explanation of model behavior. As practitioners might not only be interested in finding data points influential with respect to model accuracy, but also with respect to other important metrics, we show how to evaluate training data points on the basis of group fairness. Our method can identify unfairness-inducing training points, which can be removed to improve fairness outcomes. Our quantitative experiments and user studies show that visualizing DIVINE points helps practitioners understand and explain model behavior better than earlier approaches.

【21】 Q-SMASH: Q-Learning-based Self-Adaptation of Human-Centered Internet of Things 标题：Q-SMASH：基于Q-学习的以人为中心的物联网自适应

作者：Hamed Rahimi,Iago Felipe Trentin,Fano Ramparany,Olivier Boissier 机构：ID, Orange Labs, Meylan, France, Univ. Lyon, Universite Jean Monnet, Saint-Etienne, France, Mines Saint-Etienne, Univ. Clermont Auvergne, CNRS, UMR , LIMOS, Institut Henri Fayol, Saint-Etienne, France 备注：Submitted to wi-iat2021. arXiv admin note: text overlap with arXiv:2105.14915 链接：https://arxiv.org/abs/2107.05949 摘要：随着以人为中心的物联网（HCIoT）应用数量的增加，其服务和设备的自适应成为解决决策过程中环境不确定性的基本要求。HCIoT的自适应旨在管理动态环境中的运行时变化，并调整IoT对象的功能，以便在执行过程中实现期望的目标。SMASH是一个语义支持的多智能体系统，它能使物联网对象自主地适应环境的不确定性。SMASH只解决了物联网应用的自适应问题，而没有解决用户的行为问题。提出了一种基于多智能体强化学习的物联网对象自适应方法Q-SMASH。Q-SMASH旨在了解用户的行为，同时尊重人类的价值观。Q-SMASH的学习能力使其能够适应用户的行为变化，在不同的状态和情况下做出更准确的决策。 摘要：As the number of Human-Centered Internet of Things (HCIoT) applications increases, the self-adaptation of its services and devices is becoming a fundamental requirement for addressing the uncertainties of the environment in decision-making processes. Self-adaptation of HCIoT aims to manage run-time changes in a dynamic environment and to adjust the functionality of IoT objects in order to achieve desired goals during execution. SMASH is a semantic-enabled multi-agent system for self-adaptation of HCIoT that autonomously adapts IoT objects to uncertainties of their environment. SMASH addresses the self-adaptation of IoT applications only according to the human values of users, while the behavior of users is not addressed. This article presents Q-SMASH: a multi-agent reinforcement learning-based approach for self-adaptation of IoT objects in human-centered environments. Q-SMASH aims to learn the behaviors of users along with respecting human values. The learning ability of Q-SMASH allows it to adapt itself to the behavioral change of users and make more accurate decisions in different states and situations.

【22】 On Designing Good Representation Learning Models 标题：论设计良好的表征学习模式

作者：Qinglin Li,Bin Li,Jonathan M Garibaldi,Guoping Qiu 备注：15 pages, 链接：https://arxiv.org/abs/2107.05948 摘要：表征学习的目标不同于决策等机器学习的最终目标，因此很难建立清晰直接的表征学习模型训练目标。有人认为，一个好的代表应该解开潜在的变异因素，但如何将其转化为训练目标仍然是未知的。本文试图建立直接训练准则和设计原则，以发展良好的表征学习模型。我们提出一个好的表征学习模型应该具有最大的表达能力，即能够区分最大数量的输入配置。我们正式定义了表达性，并引入了一般学习模型的最大表达性定理。我们建议训练一个模型，最大限度地提高其表达能力，同时纳入一般的先验知识，如模型的光滑性。提出了一种良心竞争学习算法，该算法在保证模型光滑性的前提下，使模型达到mex。我们还引入了标签一致性训练（LCT）技术，通过鼓励模型为相似的样本分配一致的标签来提高模型的平滑度。我们提出了大量的实验结果表明，我们的方法确实可以设计出表征学习模型，能够开发出与现有技术相当或更好的表征。我们还表明，我们的技术计算效率高，对不同的参数设置具有鲁棒性，可以有效地处理各种数据集。 摘要：The goal of representation learning is different from the ultimate objective of machine learning such as decision making, it is therefore very difficult to establish clear and direct objectives for training representation learning models. It has been argued that a good representation should disentangle the underlying variation factors, yet how to translate this into training objectives remains unknown. This paper presents an attempt to establish direct training criterions and design principles for developing good representation learning models. We propose that a good representation learning model should be maximally expressive, i.e., capable of distinguishing the maximum number of input configurations. We formally define expressiveness and introduce the maximum expressiveness (MEXS) theorem of a general learning model. We propose to train a model by maximizing its expressiveness while at the same time incorporating general priors such as model smoothness. We present a conscience competitive learning algorithm which encourages the model to reach its MEXS whilst at the same time adheres to model smoothness prior. We also introduce a label consistent training (LCT) technique to boost model smoothness by encouraging it to assign consistent labels to similar samples. We present extensive experimental results to show that our method can indeed design representation learning models capable of developing representations that are as good as or better than state of the art. We also show that our technique is computationally efficient, robust against different parameter settings and can work effectively on a variety of datasets.

【23】 HAT: Hierarchical Aggregation Transformers for Person Re-identification 标题：HAT：用于人员重新识别的分层聚合转换器

作者：Guowen Zhang,Pingping Zhang,Jinqing Qi,Huchuan Lu 机构：Dalian University of Technology, Dalian, Liaoning, China 备注：This work has been accepted by ACM International Conference on Multimedia 2021.To our best knowledge, this work is the very first to take advantages of both CNNs and Transformers for image-based person Re-ID 链接：https://arxiv.org/abs/2107.05946 摘要：近年来，随着深度卷积神经网络（CNNs）的发展，人员再识别（Re-ID）在各种应用中取得了巨大的成功。然而，由于CNNs的感受野有限，在非重叠摄像机下，如何在全局视野中提取出有区别的表征仍然是一个挑战。同时，Transformers对空间和序列数据的长期依赖性建模能力很强。本文综合CNNs和Transformers的优点，提出了一种新的基于图像的高性能person-Re-ID学习框架HAT。为了实现这一目标，我们首先提出了一种深度监督聚合（DSA）方法来循环聚合CNN主干的层次特征。DSA通过多粒度监控，增强了多尺度特征，实现了不同于以往方法的人物检索。然后，我们引入了一种基于变换的特征校正（TFC）方法来整合低层细节信息，作为高层语义信息的全局先验。提出的TFC被插入到每个层次的特征中，从而大大提高了性能。实验结果表明，本文提出的几种基于Re-ns的图像识别方法比基于cnid的大规模图像识别方法具有更好的性能。代码发布于https://github.com/AI-Zhpp/HAT. 摘要：Recently, with the advance of deep Convolutional Neural Networks (CNNs), person Re-Identification (Re-ID) has witnessed great success in various applications. However, with limited receptive fields of CNNs, it is still challenging to extract discriminative representations in a global view for persons under non-overlapped cameras. Meanwhile, Transformers demonstrate strong abilities of modeling long-range dependencies for spatial and sequential data. In this work, we take advantages of both CNNs and Transformers, and propose a novel learning framework named Hierarchical Aggregation Transformer (HAT) for image-based person Re-ID with high performance. To achieve this goal, we first propose a Deeply Supervised Aggregation (DSA) to recurrently aggregate hierarchical features from CNN backbones. With multi-granularity supervisions, the DSA can enhance multi-scale features for person retrieval, which is very different from previous methods. Then, we introduce a Transformer-based Feature Calibration (TFC) to integrate low-level detail information as the global prior for high-level semantic information. The proposed TFC is inserted to each level of hierarchical features, resulting in great performance improvements. To our best knowledge, this work is the first to take advantages of both CNNs and Transformers for image-based person Re-ID. Comprehensive experiments on four large-scale Re-ID benchmarks demonstrate that our method shows better results than several state-of-the-art methods. The code is released at https://github.com/AI-Zhpp/HAT.

【24】 The Piano Inpainting Application 标题：浅谈钢琴修复技术的应用

作者：Gaëtan Hadjeres,Léopold Crestel 机构：Sony Computer Science Laboratories, Paris, France 链接：https://arxiv.org/abs/2107.05944 摘要：自回归模型现在能够产生高品质的分钟长的表现力MIDI钢琴表演。尽管这一进展提出了新的工具来辅助音乐创作，但我们观察到，由于生成算法提供的控制有限、推理时间过长或音乐家的工作流程中缺乏集成，因此生成算法仍然没有被艺术家广泛使用。在这项工作中，我们提出了钢琴修复应用程序（PIA），一个专注于修复钢琴演奏的生成模型，因为我们相信这种基本操作（修复钢琴演奏中缺失的部分）鼓励了人机交互，并为音乐创作开辟了新的途径。我们的方法依赖于一个编码器-解码器线性Transformer结构，该结构基于一种称为结构化MIDI编码的MIDI钢琴演奏的新表示法。通过揭示线性Transformer和我们的修复任务之间有趣的协同作用，我们能够有效地修复钢琴演奏的相邻区域，这使得我们的模型适合交互式和响应性人工智能辅助创作。最后，我们介绍我们免费提供的Ableton Live PIA插件，它允许音乐家在广泛使用的专业数字音频工作站中使用PIA平滑地生成或修改任何MIDI剪辑。 摘要：Autoregressive models are now capable of generating high-quality minute-long expressive MIDI piano performances. Even though this progress suggests new tools to assist music composition, we observe that generative algorithms are still not widely used by artists due to the limited control they offer, prohibitive inference times or the lack of integration within musicians' workflows. In this work, we present the Piano Inpainting Application (PIA), a generative model focused on inpainting piano performances, as we believe that this elementary operation (restoring missing parts of a piano performance) encourages human-machine interaction and opens up new ways to approach music composition. Our approach relies on an encoder-decoder Linear Transformer architecture trained on a novel representation for MIDI piano performances termed Structured MIDI Encoding. By uncovering an interesting synergy between Linear Transformers and our inpainting task, we are able to efficiently inpaint contiguous regions of a piano performance, which makes our model suitable for interactive and responsive A.I.-assisted composition. Finally, we introduce our freely-available Ableton Live PIA plugin, which allows musicians to smoothly generate or modify any MIDI clip using PIA within a widely-used professional Digital Audio Workstation.

【25】 Towards Representation Identical Privacy-Preserving Graph Neural Network via Split Learning 标题：基于分裂学习的表示一致保密图神经网络

作者：Chuanqiang Shan,Huiyun Jiao,Jie Fu 链接：https://arxiv.org/abs/2107.05917 摘要：近年来，随着对图神经网络（GNN）研究数量的迅速增加，它已从理论研究走向实际应用阶段。尽管GNN取得了令人鼓舞的性能，但是在相关文献中，对分布式图形数据的隐私保护训练和推理的关注较少。由于图结构的特殊性，将现有的私有学习框架扩展到GNN具有挑战性。基于分裂学习的思想，我们提出了一种用于水平分区跨思洛存储器场景的节点级任务的\textbf{S}server\textbf{a}ided\textbf{P}竞争保持\textbf{GNN}（SAPGNN）。它将集中式GNN自然地扩展到具有max/min池聚合的孤立图，同时保证所有参与计算的私有数据仍然保留在本地数据持有者。为了进一步提高数据的保密性，提出了一种安全的池聚合机制。理论和实验结果表明，该模型与在组合数据上学习的模型具有相同的精度。 摘要：In recent years, the fast rise in number of studies on graph neural network (GNN) has put it from the theories research to reality application stage. Despite the encouraging performance achieved by GNN, less attention has been paid to the privacy-preserving training and inference over distributed graph data in the related literature. Due to the particularity of graph structure, it is challenging to extend the existing private learning framework to GNN. Motivated by the idea of split learning, we propose a \textbf{S}erver \textbf{A}ided \textbf{P}rivacy-preserving \textbf{GNN} (SAPGNN) for the node level task on horizontally partitioned cross-silo scenario. It offers a natural extension of centralized GNN to isolated graph with max/min pooling aggregation, while guaranteeing that all the private data involved in computation still stays at local data holders. To further enhancing the data privacy, a secure pooling aggregation mechanism is proposed. Theoretical and experimental results show that the proposed model achieves the same accuracy as the one learned over the combined data.

【26】 Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music 标题：在符号多声道音乐中学习分离声部走向自动化乐器

作者：Hao-Wen Dong,Chris Donahue,Taylor Berg-Kirkpatrick,Julian McAuley 机构： University of California San Diego, Stanford University 备注：Accepted to ISMIR 2021 链接：https://arxiv.org/abs/2107.05916 摘要：现代键盘允许音乐家同时演奏多种乐器，方法是给不同的乐器指定区域——键盘的固定音高范围。在本文中，我们旨在进一步扩展这一思想，并探讨自动乐器的可行性，即在独奏音乐演奏过程中为音符动态分配乐器。除了为执行用例提供在线、实时的设置外，自动插装还可以在离线设置中的辅助创作工具中找到应用程序。由于缺乏原始独奏音乐的配对数据及其完整排列，我们通过学习将部分（如声音、乐器和音轨）从符号多轨音乐的混合中分离出来，假设混合是在键盘上播放的，从而接近自动乐器。我们将零件分离问题定义为一个序列多类分类问题，并采用机器学习将注释序列映射为零件标签序列。为了检验我们提出的模型的有效性，我们对巴赫合唱、弦乐四重奏、游戏音乐和流行音乐四个不同流派和合奏的数据集进行了全面的实证评估。我们的实验表明，所提出的模型优于各种基线。我们还展示了我们提出的模型通过将混合物分成若干部分，为现有安排产生替代的令人信服的工具的潜力。所有源代码和音频样本可以在https://salu133445.github.io/arranger/ . 摘要：Modern keyboards allow a musician to play multiple instruments at the same time by assigning zones -- fixed pitch ranges of the keyboard -- to different instruments. In this paper, we aim to further extend this idea and examine the feasibility of automatic instrumentation -- dynamically assigning instruments to notes in solo music during performance. In addition to the online, real-time-capable setting for performative use cases, automatic instrumentation can also find applications in assistive composing tools in an offline setting. Due to the lack of paired data of original solo music and their full arrangements, we approach automatic instrumentation by learning to separate parts (e.g., voices, instruments and tracks) from their mixture in symbolic multitrack music, assuming that the mixture is to be played on a keyboard. We frame the task of part separation as a sequential multi-class classification problem and adopt machine learning to map sequences of notes into sequences of part labels. To examine the effectiveness of our proposed models, we conduct a comprehensive empirical evaluation over four diverse datasets of different genres and ensembles -- Bach chorales, string quartets, game music and pop music. Our experiments show that the proposed models outperform various baselines. We also demonstrate the potential for our proposed models to produce alternative convincing instrumentations for an existing arrangement by separating its mixture into parts. All source code and audio samples can be found at https://salu133445.github.io/arranger/ .

【27】 Region attention and graph embedding network for occlusion objective class-based micro-expression recognition 标题：基于遮挡目标类的区域注意力和图形嵌入网络微表情识别

作者：Qirong Mao,Ling Zhou,Wenming Zheng,Xiuyan Shao,Xiaohua Huang 机构： China and also with the School of Biological Science andMedical Engineering, Southeast University 链接：https://arxiv.org/abs/2107.05904 摘要：微表情识别（Micro expression recognition，简称MER）近十年来引起了众多研究者的关注。然而，在真实场景中，MER会发生遮挡。本文深入研究了MER中一个有趣但尚未探索的具有挑战性的问题，即阻塞MER。首先，为了研究真实遮挡下的MER，利用不同的掩模为社区创建了综合遮挡微表情数据库。第二，为了抑制遮挡的影响，提出了一种基于区域启发的关联网络来模拟不同面部区域之间的关系。RRRN由主干网、区域启发（\textbf{RI}）模块和关系推理（\textbf{RR}）模块组成。更具体地说，骨干网的目的是从不同的面部区域中提取特征表示，RI模块根据无障碍性和抑制遮挡影响的重要性，基于注意机制从区域本身计算自适应权重，RR模块通过执行图卷积来利用这些区域之间的渐进交互。对megc2018协议的讲义数据库评价和复合数据库评价任务进行了实验研究。实验结果表明，RRRN能有效地挖掘面部区域的重要性，并捕捉到MER中面部区域的合作互补关系。结果还表明，RRRN的性能优于现有的方法，特别是在遮挡方面，而且RRRN对遮挡的鲁棒性更强。 摘要：Micro-expression recognition (\textbf{MER}) has attracted lots of researchers' attention in a decade. However, occlusion will occur for MER in real-world scenarios. This paper deeply investigates an interesting but unexplored challenging issue in MER, \ie, occlusion MER. First, to research MER under real-world occlusion, synthetic occluded micro-expression databases are created by using various mask for the community. Second, to suppress the influence of occlusion, a \underline{R}egion-inspired \underline{R}elation \underline{R}easoning \underline{N}etwork (\textbf{RRRN}) is proposed to model relations between various facial regions. RRRN consists of a backbone network, the Region-Inspired (\textbf{RI}) module and Relation Reasoning (\textbf{RR}) module. More specifically, the backbone network aims at extracting feature representations from different facial regions, RI module computing an adaptive weight from the region itself based on attention mechanism with respect to the unobstructedness and importance for suppressing the influence of occlusion, and RR module exploiting the progressive interactions among these regions by performing graph convolutions. Experiments are conducted on handout-database evaluation and composite database evaluation tasks of MEGC 2018 protocol. Experimental results show that RRRN can significantly explore the importance of facial regions and capture the cooperative complementary relationship of facial regions for MER. The results also demonstrate RRRN outperforms the state-of-the-art approaches, especially on occlusion, and RRRN acts more robust to occlusion.

【28】 Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition 标题：Auto IV：通过自动工具变量分解进行反事实预测

作者：Junkun Yuan,Anpeng Wu,Kun Kuang,Bo Li,Runze Wu,Fei Wu,Lanfen Lin 备注：12 pages 链接：https://arxiv.org/abs/2107.05884 摘要：工具变量（IVs）是治疗随机化的来源，与结果有条件独立，在因果推断中起着重要作用。然而，现有的基于IV的反事实预测方法需要预先定义好的IV，而在许多真实场景中找到有效的IV是一门艺术而不是科学。此外，预定义的手工IVs可能会因违反有效IVs的条件而变弱或出错。这些棘手的事实阻碍了基于IV的反事实预测方法的应用。在本文中，我们提出了一种新的自动工具变量分解（AutoIV）算法，从观察变量（IV候选者）中自动生成服务于IVs角色的表示。具体地说，我们分别通过互信息最大化和最小化约束，使学习到的IV表示满足处理的相关条件和结果的排除条件。我们还通过鼓励他们与治疗和结果相关来学习混杂因素表征。在对抗性博弈中，IV和混杂表示与它们的约束条件竞争信息，这使得我们能够得到有效的IV表示，用于基于IV的反事实预测。大量的实验表明，我们的方法生成了有效的IV表示，用于精确的基于IV的反事实预测。 摘要：Instrumental variables (IVs), sources of treatment randomization that are conditionally independent of the outcome, play an important role in causal inference with unobserved confounders. However, the existing IV-based counterfactual prediction methods need well-predefined IVs, while it's an art rather than science to find valid IVs in many real-world scenes. Moreover, the predefined hand-made IVs could be weak or erroneous by violating the conditions of valid IVs. These thorny facts hinder the application of the IV-based counterfactual prediction methods. In this paper, we propose a novel Automatic Instrumental Variable decomposition (AutoIV) algorithm to automatically generate representations serving the role of IVs from observed variables (IV candidates). Specifically, we let the learned IV representations satisfy the relevance condition with the treatment and exclusion condition with the outcome via mutual information maximization and minimization constraints, respectively. We also learn confounder representations by encouraging them to be relevant to both the treatment and the outcome. The IV and confounder representations compete for the information with their constraints in an adversarial game, which allows us to get valid IV representations for IV-based counterfactual prediction. Extensive experiments demonstrate that our method generates valid IV representations for accurate IV-based counterfactual prediction.

【29】 GA and ILS for optimizing the size of NFA models 标题：遗传算法和ILS算法在NFA模型尺寸优化中的应用

作者：Frédéric Lardeux,Eric Monfroy 机构：Univ Angers, LERIA, SFR MATHSTIC, F-, Angers, France 备注：None 链接：https://arxiv.org/abs/2107.05877 摘要：语法推理包括学习形式语法（作为一组重写规则或有限状态机）。我们关心的是学习非确定性有限自动机（NFA）的一个给定的大小从样本的积极和消极的话。NFA自然可以在SAT中建模。由于标准模型[1]非常庞大，我们还尝试了一种基于前缀[2]的模型，它可以生成更小的实例。提出了一种新的基于后缀的模型和一种基于前缀和后缀的混合模型。然后，我们将重点放在优化混合模型生成的SAT实例的大小上。我们提出了两种优化组合的方法，一种是基于迭代局部搜索（ILS），另一种是基于遗传算法（GA）。优化组合可显著减少SAT实例及其求解时间，但代价是生成时间较长。因此，通过一些实验比较，我们研究了生成时间和求解时间之间的平衡，并分析了我们的各种模型改进。 摘要：Grammatical inference consists in learning a formal grammar (as a set of rewrite rules or a finite state machine). We are concerned with learning Nondeterministic Finite Automata (NFA) of a given size from samples of positive and negative words. NFA can naturally be modeled in SAT. The standard model [1] being enormous, we also try a model based on prefixes [2] which generates smaller instances. We also propose a new model based on suffixes and a hybrid model based on prefixes and suffixes. We then focus on optimizing the size of generated SAT instances issued from the hybrid models. We present two techniques to optimize this combination, one based on Iterated Local Search (ILS), the second one based on Genetic Algorithm (GA). Optimizing the combination significantly reduces the SAT instances and their solving time, but at the cost of longer generation time. We, therefore, study the balance between generation time and solving time thanks to some experimental comparisons, and we analyze our various model improvements.

【30】 Encoding Compositionality in Classical Planning Solutions 标题：经典计划解决方案中的编码组合性

作者：Angeline Aguinaldo,William Regli 机构：University of Maryland, College Park, Johns Hopkins University Applied Physics Laboratory 备注：IJCAI Generalization in Planning Workshop 2021 链接：https://arxiv.org/abs/2107.05850 摘要：经典的人工智能计划者以长而不透明的文本输出形式提供计划问题的解决方案。为了帮助理解计划解决方案的可转移性，除了当前的逐行文本表示法之外，还需要对人和计算机具有丰富且可理解的表示法。特别是，需要对整个计划中的文本跟踪进行编码，以捕获所选操作之间的依赖关系。本文的方法是将动作视为文字之间的映射，而选定的计划则是这些映射的一个组成部分。数学理论，称为范畴论，提供了相关的结构捕捉地图，他们的组成，以及地图之间的组成。我们利用这一理论，提出了一种算法不可知，基于模型的表示领域，问题和计划表达在常用的规划描述语言，PDDL。这种范畴论表示法除了线性表示法外，还伴随着一种图形语法，类似于代数表达式，可以用来推断在计划的每一步中使用的文字。这提供了适当的构造性抽象，并有助于操作人员理解。在本文中，我们将在Blocksworld域内的一个平面图上对此进行演示。 摘要：Classical AI planners provide solutions to planning problems in the form of long and opaque text outputs. To aid in the understanding transferability of planning solutions, it is necessary to have a rich and comprehensible representation for both human and computers beyond the current line-by-line text notation. In particular, it is desirable to encode the trace of literals throughout the plan to capture the dependencies between actions selected. The approach of this paper is to view the actions as maps between literals and the selected plan as a composition of those maps. The mathematical theory, called category theory, provides the relevant structures for capturing maps, their compositions, and maps between compositions. We employ this theory to propose an algorithm agnostic, model-based representation for domains, problems, and plans expressed in the commonly used planning description language, PDDL. This category theoretic representation is accompanied by a graphical syntax in addition to a linear notation, similar to algebraic expressions, that can be used to infer literals used at every step of the plan. This provides the appropriate constructive abstraction and facilitates comprehension for human operators. In this paper, we demonstrate this on a plan within the Blocksworld domain.

【31】 Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks 标题：利用人类指导进行顺序决策任务的最新进展

作者：Ruohan Zhang,Faraz Torabi,Garrett Warnell,Peter Stone 机构：Contributed equally to this work 1Department of Computer Science, The University of Texas at Austin 2U 备注：None 链接：https://arxiv.org/abs/2107.05825 摘要：人工智能的一个长期目标是创建能够学习执行需要顺序决策的任务的人工代理。重要的是，虽然学习和行动的是人工智能体，但仍由人类来指定要执行的特定任务。经典的任务规格说明方法通常涉及人类提供固定的奖励函数或显式演示所需的任务。然而，最近有大量的研究精力投入到探索人类引导学习代理的替代方法上，例如，可以更适合某些任务或需要更少的人力。这项调查提供了一个高层次的概述，五个最近的机器学习框架，主要依赖于人类的指导，除了预先指定的奖励功能或传统的，一步一步的行动示范。我们回顾了每个框架的动机、假设和实现，并讨论了未来可能的研究方向。 摘要：A longstanding goal of artificial intelligence is to create artificial agents capable of learning to perform tasks that require sequential decision making. Importantly, while it is the artificial agent that learns and acts, it is still up to humans to specify the particular task to be performed. Classical task-specification approaches typically involve humans providing stationary reward functions or explicit demonstrations of the desired tasks. However, there has recently been a great deal of research energy invested in exploring alternative ways in which humans may guide learning agents that may, e.g., be more suitable for certain tasks or require less human effort. This survey provides a high-level overview of five recent machine learning frameworks that primarily rely on human guidance apart from pre-specified reward functions or conventional, step-by-step action demonstrations. We review the motivation, assumptions, and implementation of each framework, and we discuss possible future research directions.

【32】 AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training 标题：AlterSGD：通过另类训练找到适合持续学习的扁平迷你图

作者：Zhongzhan Huang,Mingfu Liang,Senwei Liang,Wei He 机构：Tsinghua University, Northwestern University, Purdue University, Nanyang Technological University 链接：https://arxiv.org/abs/2107.05804 摘要：深度神经网络在连续学习多个知识时会遭受灾难性遗忘，越来越多的方法被提出来缓解这一问题。其中一些方法通过将平坦的局部极小值与持续学习中的遗忘缓解联系起来，取得了相当好的效果。然而，它们不可避免地需要（1）繁琐的超参数调整，（2）额外的计算成本。为了缓解这些问题，本文提出了一种简单而有效的优化方法AlterSGD，用于在损失景观中寻找平坦的最小值。在AlterSGD中，当网络在每次学习新知识时趋于收敛时，我们交替进行梯度下降和上升。此外，我们从理论上证明了这样的策略可以鼓励优化收敛到平坦的极小值。我们在语义切分的连续学习基准上验证了AlterSGD，实验结果表明，在具有挑战性的连续学习协议下，AlterSGD能够显著地减少遗忘，并在很大程度上优于现有的方法。 摘要：Deep neural networks suffer from catastrophic forgetting when learning multiple knowledge sequentially, and a growing number of approaches have been proposed to mitigate this problem. Some of these methods achieved considerable performance by associating the flat local minima with forgetting mitigation in continual learning. However, they inevitably need (1) tedious hyperparameters tuning, and (2) additional computational cost. To alleviate these problems, in this paper, we propose a simple yet effective optimization method, called AlterSGD, to search for a flat minima in the loss landscape. In AlterSGD, we conduct gradient descent and ascent alternatively when the network tends to converge at each session of learning new knowledge. Moreover, we theoretically prove that such a strategy can encourage the optimization to converge to a flat minima. We verify AlterSGD on continual learning benchmark for semantic segmentation and the empirical results show that we can significantly mitigate the forgetting and outperform the state-of-the-art methods with a large margin under challenging continual learning protocols.

【33】 Deep Neural Networks Evolve Human-like Attention Distribution during Reading Comprehension 标题：深度神经网络在阅读理解过程中的类人注意力分布

作者：Jiajie Zou,Nai Ding 机构：Zhejiang lab; College of Biomedical Engineering and Instrument Sciences, Zhejiang University, Hangzhou , China, Key Laboratory for Biomedical Engineering of Ministry of Education, Corresponding author: 链接：https://arxiv.org/abs/2107.05799 摘要：注意是生物大脑和许多先进的深层神经网络（DNNs）中信息选择的关键机制。在这里，我们调查人类和dnn在阅读一篇文章以回答一个特定问题时是否以类似的方式分配注意力。我们分析了3个基于Transformer的dnn，当训练他们执行阅读理解任务时，这些dnn达到了人的水平。我们发现，DNN的注意力分布在数量上类似于人类的注意力分布测量注视时间。人类读者对与答疑任务更相关的单词的关注时间更长，这表明注意力是由自上而下的阅读目标调节的，而不是刺激的较低层次的视觉和文本特征。进一步的分析表明，DNNs的注意权重同时受自上而下阅读目标和低水平刺激特征的影响，浅层受低水平文本特征的影响更大，而深层更关注任务相关词。此外，当预训练的DNN模型被微调以执行阅读理解任务时，深层对任务相关词的注意逐渐显现，这与任务绩效的提高相吻合。这些结果表明，DNNs可以通过任务优化进化出类人的注意分布，这说明目标导向阅读理解中的人的注意是任务优化的结果。 摘要：Attention is a key mechanism for information selection in both biological brains and many state-of-the-art deep neural networks (DNNs). Here, we investigate whether humans and DNNs allocate attention in comparable ways when reading a text passage to subsequently answer a specific question. We analyze 3 transformer-based DNNs that reach human-level performance when trained to perform the reading comprehension task. We find that the DNN attention distribution quantitatively resembles human attention distribution measured by fixation times. Human readers fixate longer on words that are more relevant to the question-answering task, demonstrating that attention is modulated by top-down reading goals, on top of lower-level visual and text features of the stimulus. Further analyses reveal that the attention weights in DNNs are also influenced by both top-down reading goals and lower-level stimulus features, with the shallow layers more strongly influenced by lower-level text features and the deep layers attending more to task-relevant words. Additionally, deep layers' attention to task-relevant words gradually emerges when pre-trained DNN models are fine-tuned to perform the reading comprehension task, which coincides with the improvement in task performance. These results demonstrate that DNNs can evolve human-like attention distribution through task optimization, which suggests that human attention during goal-directed reading comprehension is a consequence of task optimization.

【34】 Cautious Policy Programming: Exploiting KL Regularization in Monotonic Policy Improvement for Reinforcement Learning 标题：谨慎的策略规划：在强化学习的单调策略改进中利用KL正则化

作者：Lingwei Zhu,Toshinori Kitamura,Takamitsu Matsubara 机构：Graduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma, Nara, Japan 备注：15 pages. arXiv admin note: text overlap with arXiv:2008.10806 链接：https://arxiv.org/abs/2107.05798 摘要：本文提出了一种新的基于值的强化学习（RL）算法&谨慎策略规划（CPP），该算法能保证学习过程中策略的单调性。基于熵正则化RL的性质，提出了一种新的熵正则化策略改进下界，该下界只需要估计期望的策略优势函数。CPP利用这个下限作为调整策略更新程度的标准，以减轻策略振荡。不同于类似的算法大多是面向理论的，我们还提出了一种新的插值方案，使CPP在高维控制问题中具有更好的规模。我们证明了所提出的算法可以交易o？在说教经典控制问题和具有挑战性的高维Atari游戏中的性能和稳定性。 摘要：In this paper, we propose cautious policy programming (CPP), a novel value-based reinforcement learning (RL) algorithm that can ensure monotonic policy improvement during learning. Based on the nature of entropy-regularized RL, we derive a new entropy regularization-aware lower bound of policy improvement that only requires estimating the expected policy advantage function. CPP leverages this lower bound as a criterion for adjusting the degree of a policy update for alleviating policy oscillation. Different from similar algorithms that are mostly theory-oriented, we also propose a novel interpolation scheme that makes CPP better scale in high dimensional control problems. We demonstrate that the proposed algorithm can trade o? performance and stability in both didactic classic control problems and challenging high-dimensional Atari games.

【35】 Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities 标题：KIT-Net：将新的3D对象装入新的3D腔的自监督学习

作者：Shivin Devgon,Jeffrey Ichnowski,Michael Danielczuk,Daniel S. Brown,Ashwin Balakrishna,Shirin Joshi,Eduardo M. C. Rocha,Eugen Solowjow,Ken Goldberg 机构： 1TheAUTOLABattheUniversityofCalifornia 备注：None 链接：https://arxiv.org/abs/2107.05789 摘要：在工业零件装配中，三维物体被插入型腔中进行运输或后续装配。配套是一个关键的步骤，因为它可以减少下游加工和处理时间，并使较低的存储和运输成本。我们提出了Kit-Net，一个框架，用于将以前看不见的三维物体装配成空腔，给出目标空腔和一个物体在未知初始方向上被夹钳夹住的深度图像。Kit-Net采用自监督深度学习和数据增强的方法训练卷积神经网络（CNN），利用模拟深度图像对的大型训练数据集，鲁棒地估计物体之间的三维旋转，并匹配凹腔或凸腔。然后，Kit-Net使用训练好的CNN来实现一个控制器来定位和定位新的物体，以便插入到新的棱柱形和共形三维腔中。仿真实验表明，Kit网能使目标网格与目标空腔的平均相交体积达到98.9%。用工业物体进行的物理实验在使用基线方法的试验中成功率为18%，在使用Kit-Net的试验中成功率为63%。视频、代码和数据可在https://github.com/BerkeleyAutomation/Kit-Net. 摘要：In industrial part kitting, 3D objects are inserted into cavities for transportation or subsequent assembly. Kitting is a critical step as it can decrease downstream processing and handling times and enable lower storage and shipping costs. We present Kit-Net, a framework for kitting previously unseen 3D objects into cavities given depth images of both the target cavity and an object held by a gripper in an unknown initial orientation. Kit-Net uses self-supervised deep learning and data augmentation to train a convolutional neural network (CNN) to robustly estimate 3D rotations between objects and matching concave or convex cavities using a large training dataset of simulated depth images pairs. Kit-Net then uses the trained CNN to implement a controller to orient and position novel objects for insertion into novel prismatic and conformal 3D cavities. Experiments in simulation suggest that Kit-Net can orient objects to have a 98.9% average intersection volume between the object mesh and that of the target cavity. Physical experiments with industrial objects succeed in 18% of trials using a baseline method and in 63% of trials with Kit-Net. Video, code, and data are available at https://github.com/BerkeleyAutomation/Kit-Net.

【36】 Carle's Game: An Open-Ended Challenge in Exploratory Machine Creativity 标题：Carle‘s Game：探索性机器创造力的无限制挑战

作者：Q. Tyrell Davis 备注：8 pages, 11 figures, accepted to IEEE Conference on Games 2021: 978-1-6654-3886-5/21/$31.00 \copyright 2021 IEEE 链接：https://arxiv.org/abs/2107.05786 摘要：本文既是引言，又是邀请函。这是对CARLE的介绍，CARLE是一个类似生命的元胞自动机模拟器和强化学习环境。这也是一个邀请卡尔的游戏，在开放式机器探索和创造力的挑战。诱导机器智能体在跨多个细胞自动机世界创建有趣的模式方面表现出色是一项重大挑战，而解决这一挑战可能需要来自人工生命、人工智能、机器学习和复杂性等多个感兴趣领域的贡献。Carle的游戏是基于机器代理与Carle的交互，Carle是一个元胞自动机强化学习环境。卡尔是灵活的，能够模拟262144个不同的规则定义生命一样的细胞自动机宇宙。CARLE速度也很快，通过矢量化和GPU加速相结合，可以以每秒数万步的速度模拟自动机世界。最后，卡尔很简单。与为人类玩家设计的高保真物理模拟器和视频游戏相比，CARLE的二维网格世界提供了一个离散的、确定性的、原子的通用游戏场，尽管它很复杂。结合CARLE，CARLE的游戏提供了一组初始的代理策略、学习和元学习算法，以及奖励包装器，这些包装器可以定制为鼓励探索或特定任务。 摘要：This paper is both an introduction and an invitation. It is an introduction to CARLE, a Life-like cellular automata simulator and reinforcement learning environment. It is also an invitation to Carle's Game, a challenge in open-ended machine exploration and creativity. Inducing machine agents to excel at creating interesting patterns across multiple cellular automata universes is a substantial challenge, and approaching this challenge is likely to require contributions from the fields of artificial life, AI, machine learning, and complexity, at multiple levels of interest. Carle's Game is based on machine agent interaction with CARLE, a Cellular Automata Reinforcement Learning Environment. CARLE is flexible, capable of simulating any of the 262,144 different rules defining Life-like cellular automaton universes. CARLE is also fast and can simulate automata universes at a rate of tens of thousands of steps per second through a combination of vectorization and GPU acceleration. Finally, CARLE is simple. Compared to high-fidelity physics simulators and video games designed for human players, CARLE's two-dimensional grid world offers a discrete, deterministic, and atomic universal playground, despite its complexity. In combination with CARLE, Carle's Game offers an initial set of agent policies, learning and meta-learning algorithms, and reward wrappers that can be tailored to encourage exploration or specific tasks.

【37】 An active dendritic tree can mitigate fan-in limitations in superconducting neurons 标题：一棵活跃的树状树状结构可以减轻超导神经元的扇入限制。

作者：Bryce A. Primavera,Jeffrey M. Shainline 机构：Department of Physics, University of Colorado Boulder, National Institute of Standards and Technology 备注：8 pages, 5 figures 链接：https://arxiv.org/abs/2107.05777 摘要：超导电子电路在神经形态硬件方面有很多可提供的。超导量子干涉器件（SQUIDs）可以作为神经元胞体阈值操作的有源元件。然而，SQUID在应用信号中具有周期性的响应函数。我们从理论上证明，如果一个人限制对鱿鱼的总输入以维持一个单调递增的反应，那么一大部分突触必须是活跃的，以驱动神经元达到阈值。然后我们证明了一个活跃的树突树（也基于SQUIDs）可以显著减少突触的比例，这些突触必须活跃才能驱动神经元达到阈值。在这种情况下，树突树的加入提供了增强每个神经元的计算能力和允许神经元以稀疏的输入活动尖峰的双重好处。 摘要：Superconducting electronic circuits have much to offer with regard to neuromorphic hardware. Superconducting quantum interference devices (SQUIDs) can serve as an active element to perform the thresholding operation of a neuron's soma. However, a SQUID has a response function that is periodic in the applied signal. We show theoretically that if one restricts the total input to a SQUID to maintain a monotonically increasing response, a large fraction of synapses must be active to drive a neuron to threshold. We then demonstrate that an active dendritic tree (also based on SQUIDs) can significantly reduce the fraction of synapses that must be active to drive the neuron to threshold. In this context, the inclusion of a dendritic tree provides the dual benefits of enhancing the computational abilities of each neuron and allowing the neuron to spike with sparse input activity.

【38】 Kernel Continual Learning 标题：核心连续学习

作者：Mohammad Mahdi Derakhshani,Xiantong Zhen,Ling Shao,Cees G. M. Snoek 机构： University of Amsterdam, The Netherlands 2Inception Institute of Artificial Intelligence 备注：accepted to ICML 2021 链接：https://arxiv.org/abs/2107.05757 摘要：本文介绍了核连续学习，它是一种简单而有效的连续学习变体，利用核方法的非参数特性来解决灾难性遗忘问题。我们部署了一个情景记忆单元，为每个任务存储一个子集样本，以学习基于核岭回归的任务特定分类器。这不需要记忆回放，并且系统地避免了分类器中的任务干扰。我们进一步引入变分随机特征来学习每个任务的数据驱动内核。为此，我们将核连续学习描述为一个变分推理问题，其中一个随机Fourier基被合并为潜变量。从每个任务的核心集推断出随机Fourier基上的变分后验分布。通过这种方式，我们能够生成针对每个任务的更多信息内核，更重要的是，核心集的大小可以减少，以实现更紧凑的内存，从而在情景记忆的基础上实现更有效的连续学习。对四个基准的广泛评估证明了内核用于持续学习的有效性和前景。 摘要：This paper introduces kernel continual learning, a simple but effective variant of continual learning that leverages the non-parametric nature of kernel methods to tackle catastrophic forgetting. We deploy an episodic memory unit that stores a subset of samples for each task to learn task-specific classifiers based on kernel ridge regression. This does not require memory replay and systematically avoids task interference in the classifiers. We further introduce variational random features to learn a data-driven kernel for each task. To do so, we formulate kernel continual learning as a variational inference problem, where a random Fourier basis is incorporated as the latent variable. The variational posterior distribution over the random Fourier basis is inferred from the coreset of each task. In this way, we are able to generate more informative kernels specific to each task, and, more importantly, the coreset size can be reduced to achieve more compact memory, resulting in more efficient continual learning based on episodic memory. Extensive evaluation on four benchmarks demonstrates the effectiveness and promise of kernels for continual learning.

【39】 Reinforcement Learning based Proactive Control for Transmission Grid Resilience to Wildfire 标题：基于强化学习的输电网抗野火能力主动控制

作者：Salah U. Kadir,Subir Majumder,Ajay D. Chhokra,Abhishek Dubey,Himanshu Neema,Aron Laszka,Anurag K. Srivastava 链接：https://arxiv.org/abs/2107.05756 摘要：电网在极端事件下的运行需要操作人员在高认知负荷的应激条件下进行决策。不利动态事件下的决策支持，特别是在预测的情况下，可以辅以智能主动控制。野火期间的电力系统运行要求在考虑野火和故障传播动态的情况下，对负荷削减、线路切换和资源分配进行弹性驱动的主动控制。然而，在一个大的系统中，在一个事件中可能有大量的线路和负荷切换，使得传统的预测驱动和随机方法在计算上很困难，导致运营商经常使用贪婪算法。我们将主动控制问题建模为马尔可夫决策过程，并将其求解为时空野火传播和电力系统主动运行的集成试验台。我们改造了巨大的野火传播观测空间，并将其作为输电资产主动断电的启发式方法的一部分。我们将这种启发式与基于强化学习的主动策略相结合来控制生成资产。我们的方法允许该控制器为发电机组的一部分提供设定点，而短视操作员可以确定其余机组的设定点，从而产生共生作用。我们评估我们的方法利用ieee24节点系统映射到一个假设的地形。我们的研究结果表明，所提出的方法可以帮助运营商在极端情况下减少负荷损失，减少通过将要断电的线路的潮流，并减少不可行的潮流解决方案的可能性，这将表明违反了输电线路的短期热限值。 摘要：Power grid operation subject to an extreme event requires decision-making by human operators under stressful condition with high cognitive load. Decision support under adverse dynamic events, specially if forecasted, can be supplemented by intelligent proactive control. Power system operation during wildfires require resiliency-driven proactive control for load shedding, line switching and resource allocation considering the dynamics of the wildfire and failure propagation. However, possible number of line- and load-switching in a large system during an event make traditional prediction-driven and stochastic approaches computationally intractable, leading operators to often use greedy algorithms. We model and solve the proactive control problem as a Markov decision process and introduce an integrated testbed for spatio-temporal wildfire propagation and proactive power-system operation. We transform the enormous wildfire-propagation observation space and utilize it as part of a heuristic for proactive de-energization of transmission assets. We integrate this heuristic with a reinforcement-learning based proactive policy for controlling the generating assets. Our approach allows this controller to provide setpoints for a part of the generation fleet, while a myopic operator can determine the setpoints for the remaining set, which results in a symbiotic action. We evaluate our approach utilizing the IEEE 24-node system mapped on a hypothetical terrain. Our results show that the proposed approach can help the operator to reduce load loss during an extreme event, reduce power flow through lines that are to be de-energized, and reduce the likelihood of infeasible power-flow solutions, which would indicate violation of short-term thermal limits of transmission lines.

【40】 SoftHebb: Bayesian inference in unsupervised Hebbian soft winner-take-all networks 标题：SoftHebb：无监督Hebbian软赢家通吃网络中的贝叶斯推理

作者：Timoleon Moraitis,Dmitry Toichkin,Yansong Chua,Qinghai Guo 机构：Huawei - Zurich Research Center, Zurich, Switzerland, Moscow, Russia, Laboratories, Huawei Technologies, Shenzhen, China 链接：https://arxiv.org/abs/2107.05747 摘要：最先进的人工神经网络（ANN）需要标记数据或层间反馈，通常在生物学上是不可信的，并且容易受到人类不易受到的对抗性攻击。另一方面，Hebbian学习在winner-take-all（WTA）网络中是无监督的，前馈的，并且在生物学上是合理的。然而，除了在非常有限的假设条件下，WTA网络的目标优化理论一直缺乏。在这里，我们正式得出这样一个理论，基于生物学上看似合理，但通用的人工神经网络元素。通过Hebbian学习，网络参数保持了数据的贝叶斯生成模型。不存在监督损失函数，但网络确实最小化了其激活和输入分布之间的交叉熵。关键是一个“软”WTA，那里没有绝对的“硬”赢家神经元，以及一种特殊类型的Hebbian样的权重和偏差可塑性。我们在实践中证实了我们的理论，在手写数字（MNIST）识别中，我们的Hebbian算法SoftHebb在不访问交叉熵的情况下最小化交叉熵，并且优于更常用的基于硬WTA的方法。引人注目的是，在某些条件下，它甚至优于有监督的端到端反向传播。具体地说，在两层网络中，当训练数据只呈现一次、测试数据有噪声以及基于梯度的对抗攻击时，SoftHebb的性能优于反向传播。混淆SoftHebb的对抗性攻击也会混淆人眼。最后，该模型可以根据输入分布生成对象的插值。 摘要：State-of-the-art artificial neural networks (ANNs) require labelled data or feedback between layers, are often biologically implausible, and are vulnerable to adversarial attacks that humans are not susceptible to. On the other hand, Hebbian learning in winner-take-all (WTA) networks, is unsupervised, feed-forward, and biologically plausible. However, an objective optimization theory for WTA networks has been missing, except under very limiting assumptions. Here we derive formally such a theory, based on biologically plausible but generic ANN elements. Through Hebbian learning, network parameters maintain a Bayesian generative model of the data. There is no supervisory loss function, but the network does minimize cross-entropy between its activations and the input distribution. The key is a "soft" WTA where there is no absolute "hard" winner neuron, and a specific type of Hebbian-like plasticity of weights and biases. We confirm our theory in practice, where, in handwritten digit (MNIST) recognition, our Hebbian algorithm, SoftHebb, minimizes cross-entropy without having access to it, and outperforms the more frequently used, hard-WTA-based method. Strikingly, it even outperforms supervised end-to-end backpropagation, under certain conditions. Specifically, in a two-layered network, SoftHebb outperforms backpropagation when the training dataset is only presented once, when the testing data is noisy, and under gradient-based adversarial attacks. Adversarial attacks that confuse SoftHebb are also confusing to the human eye. Finally, the model can generate interpolations of objects from its input distribution.

【41】 Detecting Ideal Instagram Influencer Using Social Network Analysis 标题：利用社会网络分析检测理想的Instagram影响者

作者：M. M. H Dihyat,K Malik,M. A Khan,B Imran 机构：Electronic Engineering and Computer, Science (EECS), Queen Mary University of London, London, United Kingdom 链接：https://arxiv.org/abs/2107.05731 摘要：社交媒体是现代社会的一个重要方面，人们在这里分享自己的思想、观点、感受和情感。在过去的几年里，社交媒体的普及带来了数据的巨大增长。用户使用这种媒介来表达他们对各种各样的主题的想法、感受和意见，包括政治和名人。因此，社交媒体已经演变成一个有利可图的平台，供企业扩大业务范围，改善前景。本文的重点是社会网络分析（SNA）为现实世界的在线营销战略。该研究通过比较各种中心性度量来确定网络中最中心的节点，并使用线性阈值模型来了解单个用户的传播行为。综上所述，本文将不同的中心性测度与传播行为相关联，以确定网络中最具影响力的用户 摘要：Social Media is a key aspect of modern society where people share their thoughts, views, feelings and sentiments. Over the last few years, the inflation in popularity of social media has resulted in a monumental increase in data. Users use this medium to express their thoughts, feelings, and opinions on a wide variety of subjects, including politics and celebrities. Social Media has thus evolved into a lucrative platform for companies to expand their scope and improve their prospects. The paper focuses on social network analysis (SNA) for a real-world online marketing strategy. The study contributes by comparing various centrality measures to identify the most central nodes in the network and uses a linear threshold model to understand the spreading behaviour of individual users. In conclusion, the paper correlates different centrality measures and spreading behaviour to identify the most influential user in the network

【42】 Generalization of graph network inferences in higher-order probabilistic graphical models 标题：图网络推论在高阶概率图模型中的推广

作者：Yicheng Fei,Xaq Pitkow 备注：9 pages, 2 figures 链接：https://arxiv.org/abs/2107.05729 摘要：概率图形模型为描述复杂的统计结构提供了一个强有力的工具，在科学和工程中有许多实际应用，从控制机械臂到理解神经元计算。这些图形模型的一个主要挑战是，边缘化等推论对于一般图形来说是难以处理的。这些推论通常由分布式消息传递算法（如信念传播）来近似，这种算法在有圈的图上并不总是表现得很好，对于复杂的连续概率分布也不容易指定。这种困难经常出现在表达图形模型，包括棘手的高阶相互作用。本文利用定义在因子图上的图神经网络构造迭代消息传递算法，实现对涉及多变量交互的图形模型的快速近似推理。在多个图形模型族上的实验结果表明了该方法对不同尺寸图形的超分布泛化能力，并指出了该方法优于信念传播的领域。 摘要：Probabilistic graphical models provide a powerful tool to describe complex statistical structure, with many real-world applications in science and engineering from controlling robotic arms to understanding neuronal computations. A major challenge for these graphical models is that inferences such as marginalization are intractable for general graphs. These inferences are often approximated by a distributed message-passing algorithm such as Belief Propagation, which does not always perform well on graphs with cycles, nor can it always be easily specified for complex continuous probability distributions. Such difficulties arise frequently in expressive graphical models that include intractable higher-order interactions. In this paper we construct iterative message-passing algorithms using Graph Neural Networks defined on factor graphs to achieve fast approximate inference on graphical models that involve many-variable interactions. Experimental results on several families of graphical models demonstrate the out-of-distribution generalization capability of our method to different sized graphs, and indicate the domain in which our method gains advantage over Belief Propagation.

【43】 Least-Squares Linear Dilation-Erosion Regressor Trained using Stochastic Descent Gradient or the Difference of Convex Methods 标题：用随机下降梯度或凸差法训练的最小二乘线性膨胀-侵蚀回归器

作者：Angelica Lourenço Oliveira,Marcos Eduardo Valle 备注：None 链接：https://arxiv.org/abs/2107.05682 摘要：本文提出了一种混合形态神经网络的回归任务称为线性膨胀-侵蚀回归（$\ell$-DER）。简单地说，一个$\ell$-DER模型是由线性算子和初等形态算子组成的凸组合给出的。因此，它们产生连续的分段线性函数，因此是通用逼近器。除了介绍$\ell$-DER模型外，我们还提出了三种训练这些模型的方法：一种是基于随机下降梯度的方法，另一种是基于凸规划问题的差分方法。最后，我们使用14个回归任务来评估$\ell$-DER模型的性能。尽管基于SDG的方法比其他两种方法显示的速度更快，但是使用严格的凸凹规划问题训练的$\ell$-DER在最小平均绝对误差得分方面优于其他方法。 摘要：This paper presents a hybrid morphological neural network for regression tasks called linear dilation-erosion regression ($\ell$-DER). In few words, an $\ell$-DER model is given by a convex combination of the composition of linear and elementary morphological operators. As a result, they yield continuous piecewise linear functions and, thus, are universal approximators. Apart from introducing the $\ell$-DER models, we present three approaches for training these models: one based on stochastic descent gradient and two based on the difference of convex programming problems. Finally, we evaluate the performance of the $\ell$-DER model using 14 regression tasks. Although the approach based on SDG revealed faster than the other two, the $\ell$-DER trained using a disciplined convex-concave programming problem outperformed the others in terms of the least mean absolute error score.

【44】 A Deep Reinforcement Learning Approach for Traffic Signal Control Optimization 标题：一种用于交通信号控制优化的深度强化学习方法

作者：Zhenning Li,Chengzhong Xu,Guohui Zhang 机构：a University of Macau, b University of Hawaii at Manoa, Corresponding Author 链接：https://arxiv.org/abs/2107.06115 摘要：低效的交通信号控制方法会导致交通拥挤和能源浪费等问题。强化学习是一种数据驱动的自适应交通信号控制方法。虽然深度神经网络（DNN）的发展进一步增强了它的学习能力，但将深度RLs应用于多信号交叉口交通网络仍然面临着一些挑战，包括非平稳环境、探索-开发困境、多智能体训练方案、连续动作空间等，为了解决这些问题，本文首先通过扩展actor-critic策略梯度算法，提出了一种多agent深度确定性策略梯度（MADDPG）方法。MADDPG有一个集中的学习和分散的执行范例，在这个范例中，评论家使用额外的信息来简化训练过程，而演员则根据他们自己的本地观察采取行动。在城市交通仿真平台（SUMO）上对该模型进行了仿真评价。模型比较结果表明了该算法在交通信号灯控制中的有效性。 摘要：Inefficient traffic signal control methods may cause numerous problems, such as traffic congestion and waste of energy. Reinforcement learning (RL) is a trending data-driven approach for adaptive traffic signal control in complex urban traffic networks. Although the development of deep neural networks (DNN) further enhances its learning capability, there are still some challenges in applying deep RLs to transportation networks with multiple signalized intersections, including non-stationarity environment, exploration-exploitation dilemma, multi-agent training schemes, continuous action spaces, etc. In order to address these issues, this paper first proposes a multi-agent deep deterministic policy gradient (MADDPG) method by extending the actor-critic policy gradient algorithms. MADDPG has a centralized learning and decentralized execution paradigm in which critics use additional information to streamline the training process, while actors act on their own local observations. The model is evaluated via simulation on the Simulation of Urban MObility (SUMO) platform. Model comparison results show the efficiency of the proposed algorithm in controlling traffic lights.

【45】 Drug-Target Interaction Prediction with Graph Attention networks 标题：基于图注意网络的药物与靶点相互作用预测

作者：Haiyang Wang,Guangyu Zhou,Siqi Liu,Jyun-Yu Jiang,Wei Wang 机构：Wang ,∗, Zhiyuan College, Shanghai Jiao Tong University, Shanghai, China and, Department of Computer Science, University of California, Los Angeles, USA, ∗To whom correspondence should be addressed. † These authors contributed equally to this work. 链接：https://arxiv.org/abs/2107.06099 摘要：动机：预测药物-靶点相互作用（DTI）在蛋白质组学和药物研究领域具有重要意义，是生物信息学研究的热点。尽管许多机器学习方法已经成功地应用于这项任务中，但很少有人利用DTI网络中固有的异构图结构来应对这一挑战。为了更好地学习和解释DTI拓扑结构和相似性，需要有专门用于从图结构预测交互作用的方法。结果：我们提出了一个端到端的框架，DTI-GAT（药物-靶点相互作用预测与图形注意网络）的DTI预测。DTI-GAT结合了一种深层的神经网络结构，该结构利用了药物和蛋白质序列的相互作用模式和特征，并通过注意机制对图形结构数据进行操作。DTI-GAT通过自我注意机制为每个节点分配不同的注意权重，有助于解释DTI的拓扑结构。实验结果表明，DTI-GAT在二进制DTI预测问题上的性能优于现有的各种系统。此外，独立的研究结果进一步证明了我们的模型比其他传统方法具有更好的通用性。可用性：源代码和所有数据集在https://github.com/Haiyang-W/DTI-GRAPH 摘要：Motivation: Predicting Drug-Target Interaction (DTI) is a well-studied topic in bioinformatics due to its relevance in the fields of proteomics and pharmaceutical research. Although many machine learning methods have been successfully applied in this task, few of them aim at leveraging the inherent heterogeneous graph structure in the DTI network to address the challenge. For better learning and interpreting the DTI topological structure and the similarity, it is desirable to have methods specifically for predicting interactions from the graph structure. Results: We present an end-to-end framework, DTI-GAT (Drug-Target Interaction prediction with Graph Attention networks) for DTI predictions. DTI-GAT incorporates a deep neural network architecture that operates on graph-structured data with the attention mechanism, which leverages both the interaction patterns and the features of drug and protein sequences. DTI-GAT facilitates the interpretation of the DTI topological structure by assigning different attention weights to each node with the self-attention mechanism. Experimental evaluations show that DTI-GAT outperforms various state-of-the-art systems on the binary DTI prediction problem. Moreover, the independent study results further demonstrate that our model can be generalized better than other conventional methods. Availability: The source code and all datasets are available at https://github.com/Haiyang-W/DTI-GRAPH