专栏首页专知【论文推荐】最新六篇知识图谱相关论文—Zero-shot识别、卷积二维知识图谱、变分知识图谱推理、张量分解、推荐

【论文推荐】最新六篇知识图谱相关论文—Zero-shot识别、卷积二维知识图谱、变分知识图谱推理、张量分解、推荐

【导读】既昨天推出六篇知识图谱(Knowledge Graph)文章,专知内容组今天又推出最近六篇知识图谱相关文章,为大家进行介绍,欢迎查看!

1. Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs(基于语义嵌入和知识图谱零次识别)



作者:Xiaolong Wang,Yufei Ye,Abhinav Gupta

机构:Carnegie Mellon University

摘要:We consider the problem of zero-shot recognition: learning a visual classifier for a category with zero training examples, just using the word embedding of the category and its relationship to other categories, which visual data are provided. The key to dealing with the unfamiliar or novel category is to transfer knowledge obtained from familiar classes to describe the unfamiliar class. In this paper, we build upon the recently introduced Graph Convolutional Network (GCN) and propose an approach that uses both semantic embeddings and the categorical relationships to predict the classifiers. Given a learned knowledge graph (KG), our approach takes as input semantic embeddings for each node (representing visual category). After a series of graph convolutions, we predict the visual classifier for each category. During training, the visual classifiers for a few categories are given to learn the GCN parameters. At test time, these filters are used to predict the visual classifiers of unseen categories. We show that our approach is robust to noise in the KG. More importantly, our approach provides significant improvement in performance compared to the current state-of-the-art results (from 2 ~ 3% on some metrics to whopping 20% on a few).

期刊:arXiv, 2018年4月9日

网址

http://www.zhuanzhi.ai/document/bb4696cc3a31fe5e927d9148587c78c5

2. Convolutional 2D Knowledge Graph Embeddings(卷积二维知识图谱嵌入)



作者:Tim Dettmers,Pasquale Minervini,Pontus Stenetorp,Sebastian Riedel

机构:Università della Svizzera italiana

摘要:Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs. However, these models learn less expressive features than deep, multi-layer models -- which potentially limits performance. In this work, we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets. We also show that the model is highly parameter efficient, yielding the same performance as DistMult and R-GCN with 8x and 17x fewer parameters. Analysis of our model suggests that it is particularly effective at modelling nodes with high indegree -- which are common in highly-connected, complex knowledge graphs such as Freebase and YAGO3. In addition, it has been noted that the WN18 and FB15k datasets suffer from test set leakage, due to inverse relations from the training set being present in the test set -- however, the extent of this issue has so far not been quantified. We find this problem to be severe: a simple rule-based model can achieve state-of-the-art results on both WN18 and FB15k. To ensure that models are evaluated on datasets where simply exploiting inverse relations cannot yield competitive results, we investigate and validate several commonly used datasets -- deriving robust variants where necessary. We then perform experiments on these robust datasets for our own and several previously proposed models, and find that ConvE achieves state-of-the-art Mean Reciprocal Rank across all datasets.

期刊:arXiv, 2018年4月6日

网址

http://www.zhuanzhi.ai/document/d84bc355535b53ec78fa666eec3f83f4

3. Variational Knowledge Graph Reasoning(变分知识图谱推理)



作者:Wenhu Chen,Wenhan Xiong,Xifeng Yan,William Wang

机构:University of California

摘要:Inferring missing links in knowledge graphs (KG) has attracted a lot of attention from the research community. In this paper, we tackle a practical query answering task involving predicting the relation of a given entity pair. We frame this prediction problem as an inference problem in a probabilistic graphical model and aim at resolving it from a variational inference perspective. In order to model the relation between the query entity pair, we assume that there exists an underlying latent variable (paths connecting two nodes) in the KG, which carries the equivalent semantics of their relations. However, due to the intractability of connections in large KGs, we propose to use variation inference to maximize the evidence lower bound. More specifically, our framework (\textsc{Diva}) is composed of three modules, i.e. a posterior approximator, a prior (path finder), and a likelihood (path reasoner). By using variational inference, we are able to incorporate them closely into a unified architecture and jointly optimize them to perform KG reasoning. With active interactions among these sub-modules, \textsc{Diva} is better at handling noise and coping with more complex reasoning scenarios. In order to evaluate our method, we conduct the experiment of the link prediction task on multiple datasets and achieve state-of-the-art performances on both datasets.

期刊:arXiv, 2018年4月6日

网址

http://www.zhuanzhi.ai/document/8aa7f7843bcf325312cc225e3caf9d6e

4. Knowledge Completion for Generics using Guided Tensor Factorization(使用引导张量分解的泛型知识完成)



作者:Hanie Sedghi,Ashish Sabharwal

摘要:Given a knowledge base or KB containing (noisy) facts about common nouns or generics, such as "all trees produce oxygen" or "some animals live in forests", we consider the problem of inferring additional such facts at a precision similar to that of the starting KB. Such KBs capture general knowledge about the world, and are crucial for various applications such as question answering. Different from commonly studied named entity KBs such as Freebase, generics KBs involve quantification, have more complex underlying regularities, tend to be more incomplete, and violate the commonly used locally closed world assumption (LCWA). We show that existing KB completion methods struggle with this new task, and present the first approach that is successful. Our results demonstrate that external information, such as relation schemas and entity taxonomies, if used appropriately, can be a surprisingly powerful tool in this setting. First, our simple yet effective knowledge guided tensor factorization approach achieves state-of-the-art results on two generics KBs (80% precise) for science, doubling their size at 74%-86% precision. Second, our novel taxonomy guided, submodular, active learning method for collecting annotations about rare entities (e.g., oriole, a bird) is 6x more effective at inferring further new facts about them than multiple active learning baselines.

期刊:arXiv, 2018年3月29日

网址

http://www.zhuanzhi.ai/document/f2cc0bd98371dce316e67a70bec4359c

5. Learning over Knowledge-Base Embeddings for Recommendation(在知识库嵌入的基础上进行推荐)



作者:Yongfeng Zhang,Qingyao Ai,Xu Chen,Pengfei Wang

机构:Rutgers University,University of MassachuseŠs Amherst

摘要:State-of-the-art recommendation algorithms -- especially the collaborative filtering (CF) based approaches with shallow or deep models -- usually work with various unstructured information sources for recommendation, such as textual reviews, visual images, and various implicit or explicit feedbacks. Though structured knowledge bases were considered in content-based approaches, they have been largely neglected recently due to the availability of vast amount of data, and the learning power of many complex models. However, structured knowledge bases exhibit unique advantages in personalized recommendation systems. When the explicit knowledge about users and items is considered for recommendation, the system could provide highly customized recommendations based on users' historical behaviors. A great challenge for using knowledge bases for recommendation is how to integrated large-scale structured and unstructured data, while taking advantage of collaborative filtering for highly accurate performance. Recent achievements on knowledge base embedding sheds light on this problem, which makes it possible to learn user and item representations while preserving the structure of their relationship with external knowledge. In this work, we propose to reason over knowledge base embeddings for personalized recommendation. Specifically, we propose a knowledge base representation learning approach to embed heterogeneous entities for recommendation. Experimental results on real-world dataset verified the superior performance of our approach compared with state-of-the-art baselines.

期刊:arXiv, 2018年3月23日

网址

http://www.zhuanzhi.ai/document/4a7f93d4541c08412376c92c7ac72f98

6. The Web as a Knowledge-base for Answering Complex Questions(利用网络作为知识库回答复杂问题)



作者:Alon Talmor,Jonathan Berant

机构:Tel-Aviv University

摘要:Answering complex questions is a time-consuming activity for humans that requires reasoning and integration of information. Recent work on reading comprehension made headway in answering simple questions, but tackling complex questions is still an ongoing research challenge. Conversely, semantic parsers have been successful at handling compositionality, but only when the information resides in a target knowledge-base. In this paper, we present a novel framework for answering broad and complex questions, assuming answering simple questions is possible using a search engine and a reading comprehension model. We propose to decompose complex questions into a sequence of simple questions, and compute the final answer from the sequence of answers. To illustrate the viability of our approach, we create a new dataset of complex questions, ComplexWebQuestions, and present a model that decomposes questions and interacts with the web to compute an answer. We empirically demonstrate that question decomposition improves performance from 20.8 precision@1 to 27.5 precision@1 on this new dataset.

期刊:arXiv, 2018年3月18日

网址

http://www.zhuanzhi.ai/document/877232e5fa767722b5d1277cd822a82e

-END-

文章分享自微信公众号:
专知

本文参与 腾讯云自媒体分享计划 ,欢迎热爱写作的你一起参与!

如有侵权,请联系 cloudcommunity@tencent.com 删除。
登录 后参与评论
0 条评论

相关文章

  • 【论文推荐】最新七篇知识图谱相关论文—嵌入式知识、Zero-shot识别、知识图谱嵌入、网络库、变分推理、解释、弱监督

    【导读】专知内容组整理了最近七篇知识图谱(Knowledge graphs)相关文章,为大家进行介绍,欢迎查看! 1.Learning over Knowled...

    WZEARW
  • SIGIR 2021 | 推荐系统相关论文分类整理

    ACM SIGIR 2021是CCF A类会议,人工智能领域智能信息检索( Information Retrieval,IR)方向最权威的国际会议。会议专注于信...

    张小磊
  • 掌握BERT、GPT-3、图神经网络、知识图谱等大厂必备技能!

    金三银四很快就到了,铁子们做好跳槽拿高薪的准备了吗? 回想去年的算法岗,可谓是从灰飞烟灭到人间炼狱。之后的趋势都变成了这样:转行的开始转行,换专业的开始换专业...

    昱良
  • 掌握BERT、GPT-3、图神经网络、知识图谱等大厂必备技能!

    金三银四很快就到了,铁子们做好跳槽拿高薪的准备了吗? 回想去年的算法岗,可谓是从灰飞烟灭到人间炼狱。之后的趋势都变成了这样:转行的开始转行,换专业的开始换专业...

    机器学习AI算法工程
  • 【论文推荐】最新六篇知识图谱相关论文—全局关系嵌入、时序关系提取、对抗学习、远距离关系、时序知识图谱

    WZEARW
  • SFFAI分享 | 高君宇:图神经网络在视频分类中的应用【附PPT与视频资料】

    高君宇,中国科学院自动化研究所博士生,导师为徐常胜研究员。研究方向为基于深度学习的视频理解与应用。在IEEE Transaction on Image Proc...

    马上科普尚尚
  • 【论文推荐】最新七篇推荐系统相关论文—影响兴趣、知识Embeddings、 音乐推荐、非结构化、一致性、显式和隐式特征、知识图谱

    【导读】专知内容组整理了最近七篇推荐系统(Recommender System)相关文章,为大家进行介绍,欢迎查看! 1.Learning Recommenda...

    WZEARW
  • 【论文推荐】最新5篇知识图谱相关论文—强化学习、习知识图谱的表示、词义消除歧义、并行翻译嵌入、图数据库

    【导读】专知内容组整理了最近五篇知识图谱(Knowledge Graph)相关文章,为大家进行介绍,欢迎查看! 1. DeepPath: A Reinforce...

    WZEARW
  • SIGIR 2022 | 推荐系统相关论文分类整理

    ACM SIGIR 2022是CCF A类会议,人工智能领域智能信息检索( Information Retrieval,IR)方向最权威的国际会议。会议专注于信...

    对白
  • 推荐系统遇上深度学习(二十六)--知识图谱与推荐系统结合之DKN模型原理及实现

    在本系列的上一篇中,我们大致介绍了一下知识图谱在推荐系统中的一些应用,我们最后讲到知识图谱特征学习(Knowledge Graph Embedding)是最常见...

    石晓文
  • 7 Papers & Radios | 史上最大AI模型GPT-3上线;Transformer跨界做目标检测

    论文 1:Knowledge Graph Embedding for Link Prediction: A Comparative Analysis

    机器之心
  • 精选论文 | 图神经网络时间节点【附打包下载】

    最近,图神经网络广泛受到了各界的关注,基于图神经网络的模型和应用在异质图表示学习和零样本学习任务中取得了不错的效果。今天,两位主讲嘉宾为大家精选了图神经网络方法...

    马上科普尚尚
  • 推荐融合GNN,图谱、多模态竟取得了如此惊艳的效果

    说到推荐系统,就不得不面对数据稀疏和冷启动问题,怎么解决呢?美团这篇论文《Multi-Modal Knowledge Graphs for Recommende...

    炼丹笔记
  • 收藏 | 最新知识图谱论文清单(附解读、下载)

    精选 6 篇来自 EMNLP 2018、COLING 2018、ISWC 2018 和 IJCAI 2018 的知识图谱相关工作,带你快速了解知识图谱领域最新研...

    数据派THU

扫码关注云+社区

领取腾讯云代金券