NeurIPS图表示学习研讨会录取论文揭晓:92篇论文看懂图表示学习

AI WORLD 2019 世界人工智能峰会精彩重放!

10 月 18 日,2019 中关村论坛平行论坛 ——AI WORLD 2019 世界人工智能峰会在北京启幕。新智元杨静、科大讯飞胡郁、微软王永东、华为王成录、英特尔宋继强、旷视及智源学者孙剑、滴滴叶杰平、AWS 张峥、依图颜水成、地平线黄畅、autowise.ai 黄超等重磅嘉宾中关村论剑,重启充满创新活力的 AI 未来。峰会现场,新智元揭晓 AI Era 创新大奖,并重磅发布 AI 开放创新平台和献礼新书《智周万物:人工智能改变中国》。回放链接:

【腾讯科技】

客户端:https://view.inews.qq.com/a/TEC2019101600718500

PC端:http://v.qq.com/live/p/topic/74606/preview.html

【海淀融媒】

https://m.toutiaoimg.cn/i6748195040323062540

【新浪科技】

http://video.sina.com.cn/l/p/1728577.html


新智元报道

来源:GitHub

编辑:元子

【新智元导读】NeurIPS图表示学习研讨会录取论文揭晓,共有92篇论文入选。近年来,图表示学习的研究激增,包括用于深图嵌入的技术,卷积神经网络对图结构数据的泛化以及受信念传播启发的神经信息传递方法。图可以看作是对更简单类型的结构化数据(例如图像)的自然概括,因此,它们代表了机器学习的下一个突破口。欢迎来新智元 AI 朋友圈与大咖一起讨论~

从电信网络到量子化学,图形结构化数据在自然科学和社会科学中无处不在。如果我们希望系统可以从此类数据中进行学习,推理和生成,则在深度学习体系结构中建立关系归纳偏差至关重要。

此外,图可以看作是对更简单类型的结构化数据(例如图像)的自然概括,因此,它们代表了机器学习的下一个突破口。

近年来,图表示学习的研究激增,包括用于深图嵌入的技术,卷积神经网络对图结构数据的泛化以及受信念传播启发的神经信息传递方法。

图神经网络和相关技术的这些进步导致了许多领域的最新技术成果,包括化学合成,3D视觉,推荐系统,问题解答和社交网络分析。对此领域日益普及的最大证明也许是最近关于该主题的四篇受欢迎的评论论文发表,每篇论文都试图统一各个领域相似思想的不同表述。

这表明该主题已达到临界水平,需要召开专门的研讨会,召集研究人员共同确定有意义的感兴趣领域,讨论我们如何设计新的更好的基准,鼓励讨论并促进协作。

来自谷歌、Twitter、MIT、斯坦福等公司和高校的9位科学家共同组织了NeurIPS 2019 Workshop。

该Workshop将包括有关该领域各种方法和问题的演讲,海报和邀请演讲,包括但不限于:

  • 在图上进行监督式深度学习(例如图神经网络)
  • 互动和关系网络
  • 无监督图嵌入方法
  • 图的深层生成模型
  • 用于化学/药物设计的深度学习
  • 在manifolds,点云和计算机视觉上进行深度学习
  • 关系归纳偏差(例如,用于强化学习)
  • 基准数据集和评估方法

组织者欢迎原创研究论文,这些论文以前从未在机器学习会议或研讨会上发表过。所有被接受的论文均将以poster的形式展示,并选择三篇贡献作品进行口头演示。

除了传统的研究论文提交之外,我们还将欢迎以一页纸的形式提交的论文,描述图形表示学习领域的开放性问题和挑战。这些未解决的问题将在茶歇之前立即进行简短演讲(5-10分钟),以促进讨论。

该研讨会的主要目标是促进社区建设。随着数百名新的研究人员开始在该领域开展项目,我们希望将他们聚集在一起,以将这个快速增长的图形表示学习领域整合为一个健康而充满活力的子领域。

被接受论文列表

原创研究

  • Pre-training Graph Neural Networks. Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Žitnik, Vijay S. Pande, Percy Liang and Jure Leskovec
  • Variational Graph Convolutional Networks. Louis C. Tiao, Pantelis Elinas, Harrison Tri Tue Nguyen and Edwin V. Bonilla
  • Probabilistic End-to-End Graph-based Semi-Supervised Learning. Mariana Vargas Vieyra, Aurélien Bellet and Pascal Denis

开放问题及挑战

  • Between the Interaction of Graph Neural Networks and Semantic Web. Francisco Xavier Sumba Toral
  • Disentangling structure and position in graphs. Komal Teru and Will Hamilton
  • Approximation Power of Invariant Graph Networks. Haggai Maron, Heli Ben-Hamu and Yaron Lipman
  • Intrinsic evaluation of unsupervised node embedding. Chi Thang Duong, Dung Trung Hoang, Quoc Viet Hung Nguyen, Ha The Hien Dang and Karl Aberer
  • Leveraging Time Dependency in Graphs. Arinbjörn Kolbeinsson, Naman Shukla, Akhil Gupta and Lavanya Marla

Poster演讲

  • Node2Motif: Hierarchical Invariant Embeddings of Structured Graphs Using the Bispectrum. Sophia Sanborn, Ram Mehta, Noah Shutty and Christopher Hillar
  • Learning Hierarchical Representations in Kinematic Space. Adarsh Jamadandi and Uma Mudenagudi
  • Applying Graph Neural Networks on Heterogeneous Nodes and Edge Features. Frederik Diehl
  • Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model. Yu Chen, Lingfei Wu and Mohammed Zaki
  • Convolution, attention and structure embedding. Jean-Marc Andreoli
  • Disentangling Interpretable Generative Parameters of Random and Real-World Graphs. Niklas Stoehr, Marc Brockschmidt, Jan Stuehmer and Emine Yilmaz
  • Graph Few-shot Learning via Knowledge Transfer. Huaxiu Yao, Chuxu Zhang, Ying Wei, Meng Jiang, Suhang Wang, Junzhou Huang, Nitesh Chawla and Zhenhui (Jessie) Li
  • Group Representation Theory for Knowledge Graph Embedding. Chen Cai
  • Graph Generation with Variational Recurrent Neural Network. Shih-Yang Su, Hossein Hajimirsadeghi and Greg Mori
  • Graph Embedding VAE: A Permutation Invariant Model of Graph Structure. Tony Duan and Juho Lee
  • Learning Visual Dynamics Models of Rigid Objects using Relational Inductive Biases. Fabio Ferreira, Lin Shao, Tamim Asfour and Jeannette Bohg
  • Image-Conditioned Graph Generation for Road Network Extraction. Davide Belli and Thomas Kipf
  • Deep geometric matrix completion: Are we doing it right?. Amit Boyarski, Sanketh Vendula and Alex Bronstein
  • Curvature Graph Network. Ze Ye, Kin Sum Liu, Tengfei Ma, Jie Gao and Chao Chen
  • Sequential Edge Clustering in Temporal Multigraphs. Elahe Ghalebi, Hamidreza Mahyar, Radu Grosu, Graham Taylor and Sinead Williamson
  • Learning interpretable hierarchical node representations via Ladder Gamma VAE. Arindam Sarkar, Nikhil Mehta and Piyush Rai
  • Multimodal Neural Graph Memory Networks for Visual Question Answering. Mahmoud Khademi, Parmis Naddaf and Oliver Schulte
  • Graph Alignment Networks with Node Matching Scores. Evgeniy Faerman, Otto Voggenreiter, Felix Borutta, Tobias Emrich, Max Berrendorf and Matthias Schubert
  • Graph Attacks with Latent Variable Noise Modeling. Joey Bose, Andre Cianflone and Will Hamilton
  • Graph Representation Learning via Multi-task Knowledge Distillation. Jiaqi Ma and Qiaozhu Mei
  • IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification. Lin Meng and Jiawei Zhang
  • Diachronic Embedding for Temporal Knowledge Graph Completion. Rishab Goel, Seyed Mehran Kazemi, Marcus Brubaker and Pascal Poupart
  • Improving Graph Attention Networks with Large Margin-based Constraints. Guangtao Wang, Rex Ying, Jing Huang and Jure Leskovec
  • Representation Learning of EHR Data via Graph-Based Medical Entity Embedding. Tong Wu, Yunlong Wang, Yue Wang, Emily Zhao, Yilian Yuan and Zhi Yang
  • Active Learning for Graph Neural Networks via Node Feature Propagation. Yuexin Wu, Yichong Xu, Yiming Yang and Aarti Singh
  • On Learning Paradigms for the Travelling Salesman Problem. Chaitanya K. Joshi, Thomas Laurent and Xavier Bresson
  • GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation. Marc Brockschmidt
  • Graph Embeddings from Random Neural Features. Daniele Zambon, Cesare Alippi and Lorenzo Livi
  • Graph Structured Prediction Energy Net Algorithms. Colin Graber and Alexander Schwing
  • Meta-Graph: Few shot Link Prediction via Meta-Learning. Joey Bose, Ankit Jain, Piero Molino and Will Hamilton
  • Graph Representation Learning for Fraud Prediction: A Nearest Neighbour approach. Rafaël Van Belle, Sandra Mitrović and Jochen De Weerdt
  • Tensor Graph Neural Networks for Learning on Time Varying Graphs. Osman Asif Malik, Shashanka Ubaru, Lior Horesh, Misha E. Kilmer and Haim Avron
  • Learning representations of Logical Formulae using Graph Neural Networks. Xavier Glorot, Ankit Anand, Eser Aygün, Shibl Mourad, Pushmeet Kohli and Doina Precup
  • SELFIES: a robust representation of semantically constrained graphs with an example application in chemistry. Mario Krenn, Florian Haese, Akshat Nigam, Pascal Friederich and Alan Aspuru-Guzik
  • Predicting Propositional Satisfiability via End-to-End Learning. Chris Cameron, Rex H.-G. Chen, Jason S. Hartford and Kevin Leyton-Brown
  • Residual or Gate? Towards Deeper Graph Neural Networks for Inductive Graph Representation Learning. Binxuan Huang and Kathleen M. Carley
  • Contextual Parameter Generation for Knowledge Graph Link Prediction. George I. Stoica, Otilia Stretcu, Anthony Platanios, Tom Mitchell and Barnabas Poczos
  • DynGAN: Generative Adversarial Networks for Dynamic Network Embedding. Ayush Maheshwari, Ayush Goyal, Manjesh Kumar Hanawal and Ganesh Ramakrishnan
  • Relational Graph Representation Learning for Predicting Object Affordances. Alexia Toumpa and Anthony Cohn
  • Conditional Neural Style Transfer with Peer-Regularized Feature Transform. Jan Svoboda, Asha Anoosheh, Christian Osendorfer and Jonathan Masci
  • Learning Compositional Koopman Operators for Model-Based Control. Yunzhu Li, Hao He, Jiajun Wu, Dina Katabi and Antonio Torralba
  • PiNet: Attention Pooling for Graph Classification. Peter Meltzer, Marcelo Gutierrez Mallea and Peter Bentley
  • On Node Features for Graph Neural Networks. Chi Thang Duong, Thanh Dat Hoang, Ha The Hien Dang, Quoc Viet Hung Nguyen and Karl Aberer
  • Multi-Graph Convolutional Neural Networks for Representation Learning in Recommendation. Jianing Sun and Yingxue Zhang
  • Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks. Guillaume Salha, Romain Hennequin and Michalis Vazirgiannis
  • Differentiation of Black-Box Combinatorial Solvers. Marin Vlastelica Pogančić, Anselm Paulus, Vit Musil, Georg Martius and Michal Rolinek
  • Auto-regressive Graph Generation Modeling with Improved Evaluation Methods. Chia-Cheng Liu, Harris Chan and Kevin Luk
  • Policy Learning for Task-driven Discovery of Incomplete Networks. Peter Morales, Rajmonda Caceres, and Tina Eliassi-Rad
  • Learning interpretable disease self-representations for drug repositioning. Fabrizio Frasca, Diego Galeano, Guadalupe Gonzalez, Ivan Laponogov, Kirill Veselkov, Alberto Paccanaro and Michael Bronstein
  • Building Dynamic Knowledge Graphs from Text-based Games. Mikuláš Zelinka, Xingdi Yuan, Marc-Alexandre Côté, Romain Laroche and Adam Trischler
  • GraphMix: Improved Training of Graph Neural Networks for Semi-Supervised Learning. Vikas Verma, Alex M. Lamb, Juho Kannala, Yoshua Bengio and Jian Tang
  • Learning Node Embeddings with Exponential Family Distributions. Abdulkadir Celikkanat and Fragkiskos Malliaros
  • Group Anomaly Detection via Graph Autoencoders. Pierluca D’Oro, Ennio Nasca, Jonathan Masci and Matteo Matteucci
  • Network discovery using reinforcement learning. Harshavardhan P. Kamarthi, Priyesh Vijayan, Bryan Wilder, Balaraman Ravindran and Milind Tambe
  • A quantum hardware-induced graph kernel based on Gaussian Boson Sampling. Maria Schuld, Kamil Bradler, Robert Israel, Daiqin Su and Brajesh Gupt
  • Neural Execution of Graph Algorithms. Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell and Charles Blundell
  • Short Text Classification using Graph Convolutional Network. Kshitij Tayal, Nikhil Rao, Karthik Subbian and Saurabh Agrawal
  • Logical Expressiveness of Graph Neural Networks. Mikaël Monet, Jorge Pérez, Juan Reutter, Egor Kostylev, Pablo Barceló and Juan Pablo Silva
  • Dynamic Network Representation Learning via Gaussian Embedding. Yulong Pei, Xin Du, George Fletcher and Mykola Pechenizkiy
  • Tri-graph Information Propagation for Polypharmacy Side Effect Prediction. Hao Xu, Shengqi Sang and Haiping Lu
  • Attributed Random Walk as Matrix Factorization. Lei Chen, Shunwang Gong, Joan Bruna and Michael Bronstein
  • Graph Sequential Networks. Ming Tu, Jing Huang, Xiaodong He and Bowen Zhou
  • Dynamic Embedding on Textual Networks via a Gaussian Process. Pengyu Cheng, Yitong Li, Xinyuan Zhang, Liqun Chen, David Carlson and Lawrence Carin
  • Low-Dimensional Knowledge Graph Embeddings via Hyperbolic Rotations. Ines Chami, Adva Wolf, Frederic Sala and Christopher Ré
  • Supervised Graph Attention Network for Semi-Supervised Node Classification.Dongkwan Kim and Alice Oh
  • Community detection and collaborative filtering on zero inflated graphs using spectral clustering. Guilherme Gomes, Vinayak Rao and Jennifer Neville
  • Molecule-Augmented Attention Transformer. Łukasz Maziarka, Tomasz Danel, Slawomir Mucha, Krzysztof Rataj, Jacek Tabor and Stanislaw Jastrzebski
  • Disentangling Mixtures of Epidemics on Graphs. Jessica Hoffmann, Soumya Basu, Surbhi Goel and Constantine Caramanis
  • Transferability of Spectral Graph Convolutional Neural Networks. Ron Levie, Wei Huang, Lorenzo Bucci, Michael Bronstein and Gitta Kutyniok
  • On the Interpretability and Evaluation of Graph Representation Learning. Antonia Gogoglou, C. Bayan Bruss and Keegan Hines
  • Graph Attentional Autoencoder for Anticancer Hyperfood Prediction. Shunwang Gong, Guadalupe Gonzalez, Ivan Laponogov, Kirill Veselkov and Michael Bronstein
  • Learning interaction patterns from surface representations of protein structure. Pablo Gainza Cirauqui, Freyr Sverrisson, Federico Monti, Emanuele Rodolà, Davide Boscaini, Michael Bronstein and Bruno Correia
  • Graph-Driven Generative Models for Heterogeneous Multi-Task Learning. Wenlin Wang, Hongteng Xu, Zhe Gan and Wenqi Wang
  • Observational causal inference using network information. Yan Leng, Martin Saveski, Alex ‘Sandy’ Pentland and Dean Eckles
  • Relational Graph Representation Learning for Open-Domain Question Answering. Salvatore G. Vivona and Kaveh Hassani
  • Modeling Human Brain Connectomes using Structured Neural Networks. Uday Shankar Shanthamallu, Qunwei Li, Jayaraman Thiagarajan, Rushil Anirudh, Alan Kaplan and Peer-Timo Bremer
  • Neural Message Passing on High Order Paths. Daniel Flam-Shepherd
  • Multi-Task Learning on Graphs with Node and Graph Level Labels. Chester Holtz, Onur Atan, Ryan Carey and Tushit Jain
  • Learnable Aggregator for GCN. Li Zhang and Haiping Lu
  • Deep Generative Probabilistic Graph Neural Networks for Scene Graph Generation. Mahmoud Khademi and Oliver Schulte
  • Towards an Adaptive Skip-gram Model for Network Representation Learning. I-Chung Hsieh and Cheng-Te Li
  • R-SQAIR: Relational Sequential Attend, Infer, Repeat. Aleksandar Stanić and Jürgen Schmidhuber
  • Understanding Graph Neural Networks via Trajectory Analysis. Ziqiao Meng, Jin Dong, Zengfeng Huang and Irwin King
  • Learning Vertex Convolutional Networks for Graph Classification. Yuhang Jiao, Lixin Cui, Lu Bai and Hancock Edwin

大会组织者

Rianne van den Berg, Google Research

https://riannevdberg.github.io/

Michael Bronstein, Imperial College London/Twitter/USI Lugano

https://www.imperial.ac.uk/people/m.bronstein

William L. Hamilton, McGill University/Mila

https://williamleif.github.io/

Stefanie Jegelka, Massachusetts Institute of Technology

https://people.csail.mit.edu/stefje/

Thomas Kipf, Universiteit van Amsterdam

http://tkipf.github.io/

Jure Leskovec, Stanford University/Pinterest

https://cs.stanford.edu/~jure/

Renjie Liao, University of Toronto

http://www.cs.toronto.edu/~rjliao/

Yizhou Sun, University of California, Los Angeles

http://web.cs.ucla.edu/~yzsun/

Petar Veličković, DeepMind

https://www.cst.cam.ac.uk/~pv273/

参考链接:

https://grlearning.github.io/

本文分享自微信公众号 - 新智元(AI_era)

原文出处及转载信息见文内详细说明,如有侵权,请联系 yunjia_community@tencent.com 删除。

原始发表时间:2019-10-22

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

发表于

我来说两句

0 条评论
登录 后参与评论

相关文章

来自专栏趣谈前端

基于nodeJS从0到1实现一个CMS全栈项目(中)(含源码)

这篇文章除了会涉及node的知识,还会涉及到redis(一个高性能的key-value数据库),前端领域的javascript大部分高级技巧以及ES6语法,所以...

10520
来自专栏加米谷大数据

Hadoop架构体系

官方文档组织的非常清晰,主要由以下四个组件组成:HDFS、map-reduce、yarn、hadoop-common。

9820
来自专栏北京宏哥

Appium+python自动化(三十六)- 士兵突击许三多 - 多个appium服务启动,多个设备启动,多进程并发启动设备-并发测试 - 上(超详解)

前面课程只是启动了单个appium服务,只能控制单台设备。如果需要针对多台设备测试那么该如何处理?而且发现群里的小伙伴们也在时不时地在讨论这个问题,想知道怎么实...

21150
来自专栏全栈前端精选

AST抽象语法树——最基础的javascript重点知识,99%的人根本不了解

Javascript就像一台精妙运作的机器,我们可以用它来完成一切天马行空的构思。

9920
来自专栏卓文见识

模板注入漏洞全汇总

在MVC的设计模式下,一般从 Model 层中读取数据,然后将数据传到 View 层渲染(渲染成 HTML 文件),而 View 层一般都会用到模板引擎。

36420
来自专栏小神仙

vue学习笔记2

概念:Vue.js 允许你自定义过滤器,可被用作一些常见的文本格式化。过滤器可以用在两个地方:mustache 插值和 v-bind 表达式。过滤器应该被添加在...

9120
来自专栏Rust语言学习交流

【Rust日报】 2019-09-27:async-std v0.99.7 released

7720
来自专栏全栈前端精选

【THE LAST TIME】彻底吃透 JavaScript 执行机制

首先我们需要声明下,JavaScript 的执行和运行是两个不同概念的,执行,一般依赖于环境,比如 node、浏览器、Ringo 等, JavaScript 在...

7220
来自专栏北京宏哥

手把手告诉你如何安装多个版本的node,妈妈再也不用担心版本高低引发的一系列后遗症(非常详细,非常实用)

  最近好多人都问到node怎么同时安装多个版本? 如何配置node的环境变量,如何自如的在多个版本中切换node?还有就是自己在做appium自动化的时候,有...

11240
来自专栏CRPER折腾记

XCode升级到版本11终端出现的魔性问题修正

基本能搜索到的方案都是把那个脚本的换行符,用 vim 调整下 我一脸懵逼,我要去改哪个脚本???

11820

扫码关注云+社区

领取腾讯云代金券

年度创作总结 领取年终奖励