49篇ICLR2020高分「图机器学习GML」接受论文及代码

2020 年 1 月 18 日 专知

【导读】ICLR2020论文收到2594篇论文提交,有687篇被接受,接受率为26.5%。在关于图机器学习方面,Sergei Ivanov整理了关于图机器学习方面的高分论文,有49篇关于图机器学习论文,专知进一步整理了论文阅读欢迎查看!



总共有152篇论文在题目中包含了一个“Graph”,其中有49篇论文被接受。所有图表论文的平均评分是4.5,而被接受的论文的平均评分是6.3。




图神经网络的逻辑表达性 The Logical Expressiveness of Graph Neural Networks 

Pablo Barceló, Egor V. Kostylev, Mikael Monet, Jorge Pérez, Juan Reutter, Juan Pablo Silva

代码地址:

 https://anonymous.4open.science/r/787222e2-ad5e-4810-a788-e80f0fe7eff0/

论文地址:

https://openreview.net/forum?id=r1lZ7AEKvB


本文重点研究了图神经网络的表达特性。审稿人对作者充分且一致地回答了他们的问题表示满意,认为这是一篇应该被接受的强有力的论文



Hyper-SAGNN:一种基于自注意力的超图神经网络 Hyper-SAGNN: a self-attention based graph neural network for hypergraphs

Ruochi ZhangYuesong ZouJian Ma

代码地址:

https://drive.google.com/drive/folders/1kIOc4SlAJllUJsrr2OnZ4izIQIw2JexU?usp=sharing

论文地址:

https://openreview.net/forum?id=ryeHuJBtPH


本文介绍了一种新的神经网络模型,该模型可以表示可变尺寸的超边缘,并通过实验证明了该模型在一些问题上可以改进或匹配目前的技术水平。



3.  论节点嵌入与结构图表示的等价性,On the Equivalence between Node Embeddings and Structural Graph Representations

Balasubramaniam SrinivasanBruno Ribeiro


论文地址:

https://openreview.net/forum?id=SJxzFySKwH


本文给出了节点嵌入与结构图表示之间的关系。通过对结构节点表示的含义和节点嵌入的含义的仔细定义,利用置换群,作者在定理2中证明了节点嵌入不能表示结构表示中没有的任何额外信息。然后,本文对三个任务进行了实证实验,并在第四个任务中对理论结果进行了说明。




4.  LambdaNet:使用图神经网络的概率类型推断,LambdaNet: Probabilistic Type Inference using Graph Neural Networks

Jiayi WeiMaruth GoyalGreg DurrettIsil Dillig

论文地址:

https://openreview.net/forum?id=Hkx6hANtwH


本文提出了一种基于图神经网络的动态语言类型推理方法。Reviewer(以及区域主席)喜欢GNNs在实际问题、演示和结果中的这种新颖而有用的应用。明确的接受。



5.  定向消息传递分子图,Directional Message Passing for Molecular Graphs

Johannes KlicperaJanek GroßStephan Günnemann


论文地址:

https://openreview.net/forum?id=B1eWbxStPH

本文研究了量子化学的图神经网络,在此基础上加入了一些物理方面的创新。特别地,它在保持等方差的同时考虑方向边缘信息。



49篇完整「图机器学习GML」论文列表:


论文题目 论文地址 接受类型 打分
The Logical Expressiveness of Graph Neural Net... https://openreview.net/forum?id=r1lZ7AEKvB Accept  (Spotlight) 8
Hyper-SAGNN: a self-attention based graph neur... https://openreview.net/forum?id=ryeHuJBtPH Accept  (Poster) 8
On the Equivalence between Node Embeddings and... https://openreview.net/forum?id=SJxzFySKwH Accept  (Poster) 7.33
LambdaNet: Probabilistic Type Inference using ... https://openreview.net/forum?id=Hkx6hANtwH Accept  (Poster) 7.33
Directional Message Passing for Molecular Graphs https://openreview.net/forum?id=B1eWbxStPH Accept  (Spotlight) 7.33
What graph neural networks cannot learn: depth... https://openreview.net/forum?id=B1l2bp4YwS Accept  (Poster) 7.33
Graph Neural Networks Exponentially Lose Expre... https://openreview.net/forum?id=S1ldO2EFPr Accept  (Spotlight) 7.33
Physics-aware Difference Graph Networks for Sp... https://openreview.net/forum?id=r1gelyrtwH Accept  (Poster) 7.33
GLAD: Learning Sparse Graph Recovery https://openreview.net/forum?id=BkxpMTEtPB Accept  (Poster) 7.33
GraphZoom: A Multi-level Spectral Approach for... https://openreview.net/forum?id=r1lGO0EKDH Accept  (Talk) 7.33
DeepSphere: a graph-based spherical CNN https://openreview.net/forum?id=B1e3OlStPB Accept  (Spotlight) 6.67
Query2box: Reasoning over Knowledge Graphs in ... https://openreview.net/forum?id=BJgr4kSFDS Accept  (Poster) 6.67
Dynamically Pruned Message Passing Networks fo... https://openreview.net/forum?id=rkeuAhVKvB Accept  (Poster) 6.67
Inductive Matrix Completion Based on Graph Neu... https://openreview.net/forum?id=ByxxgCEYDS Accept  (Spotlight) 6.67
On the geometry and learning low-dimensional e... https://openreview.net/forum?id=SkxQp1StDH Accept  (Poster) 6.67
Reinforced Genetic Algorithm Learning for Opti... https://openreview.net/forum?id=rkxDoJBYPB Accept  (Poster) 6.67
Reinforcement Learning Based Graph-to-Sequence... https://openreview.net/forum?id=HygnDhEtvr Accept  (Poster) 6.67
Learning to Retrieve Reasoning Paths over Wiki... https://openreview.net/forum?id=SJgVHkrYDH Accept  (Poster) 6.67
A Fair Comparison of Graph Neural Networks for... https://openreview.net/forum?id=HygDF6NFPB Accept  (Poster) 6.67
You CAN Teach an Old Dog New Tricks! On Traini... https://openreview.net/forum?id=BkxSmlBFvr Accept  (Poster) 6.67
Geom-GCN: Geometric Graph Convolutional Networks https://openreview.net/forum?id=S1e2agrFvS Accept  (Spotlight) 6.67
HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DET... https://openreview.net/forum?id=SJeqs6EFvB Accept  (Spotlight) 6.67
Inductive representation learning on temporal ... https://openreview.net/forum?id=rJeW1yHYwH Accept  (Poster) 6.67
Measuring and Improving the Use of Graph Infor... https://openreview.net/forum?id=rkeIIkHKvS Accept  (Poster) 6.33
Memory-Based Graph Networks https://openreview.net/forum?id=r1laNeBYPB Accept  (Poster) 6
Adaptive Structural Fingerprints for Graph Att... https://openreview.net/forum?id=BJxWx0NYPr Accept  (Poster) 6
Graph Constrained Reinforcement Learning for N... https://openreview.net/forum?id=B1x6w0EtwH Accept  (Poster) 6
Graph Convolutional Reinforcement Learning https://openreview.net/forum?id=HkxdQkSYDB Accept  (Poster) 6
Inductive and Unsupervised Representation Lear... https://openreview.net/forum?id=rkem91rtDB Accept  (Poster) 6
StructPool: Structured Graph Pooling via Condi... https://openreview.net/forum?id=BJxg_hVtwH Accept  (Poster) 6
GraphSAINT: Graph Sampling Based Inductive Lea... https://openreview.net/forum?id=BJe8pkHFwS Accept  (Poster) 6
Physics-as-Inverse-Graphics: Unsupervised Phys... https://openreview.net/forum?id=BJeKwTNFvB Accept  (Poster) 6
Strategies for Pre-training Graph Neural Networks https://openreview.net/forum?id=HJlWWJSFDH Accept  (Spotlight) 6
Deep Graph Matching Consensus https://openreview.net/forum?id=HyeJf1HKvS Accept  (Poster) 6
InfoGraph: Unsupervised and Semi-supervised Gr... https://openreview.net/forum?id=r1lfF2NYvH Accept  (Spotlight) 6
Pruned Graph Scattering Transforms https://openreview.net/forum?id=rJeg7TEYwB Accept  (Poster) 6
Curvature Graph Network https://openreview.net/forum?id=BylEqnVFDB Accept  (Poster) 6
Composition-based Multi-Relational Graph Convo... https://openreview.net/forum?id=BylA_C4tPr Accept  (Poster) 6
GraphAF: a Flow-based Autoregressive Model for... https://openreview.net/forum?id=S1esMkHYPr Accept  (Poster) 6
Graph inference learning for semi-supervised c... https://openreview.net/forum?id=r1evOhEKvH Accept  (Poster) 6
Probability Calibration for Knowledge Graph Em... https://openreview.net/forum?id=S1g8K1BFwS Accept  (Poster) 5.75
Neural Execution of Graph Algorithms https://openreview.net/forum?id=SkgKO0EtvS Accept  (Poster) 5.67
Visual Representation Learning with 3D View-Co... https://openreview.net/forum?id=BJxt60VtPr Accept  (Poster) 5.25
Abstract Diagrammatic Reasoning with Multiplex... https://openreview.net/forum?id=ByxQB1BKwH Accept  (Poster) 5
FEW-SHOT LEARNING ON GRAPHS VIA SUPER-CLASSES ... https://openreview.net/forum?id=Bkeeca4Kvr Accept  (Poster) 5
Differentiable learning of numerical rules in ... https://openreview.net/forum?id=rJleKgrKwS Accept  (Poster) 5
Learning deep graph matching with channel-inde... https://openreview.net/forum?id=rJgBd2NYPH Accept  (Poster) 5
DropEdge: Towards Deep Graph Convolutional Net... https://openreview.net/forum?id=Hkx1qkrKPr Accept  (Poster) 4
Efficient Probabilistic Logic Reasoning with G... https://openreview.net/forum?id=rJg76kStwH Accept  (Poster) 2.33


参考地址:

https://medium.com/@sergei.ivanov_24894/iclr-2020-graph-papers-9bc2e90e56b0


便捷查看下载,请关注专知公众号(点击上方蓝色专知关注)

  • 后台回复“ICLRGML” 就可以获取图机器学习ICLR论文以及PPT专知资源链接索引

专知,专业可信的人工智能知识分发,让认知协作更快更好!欢迎注册登录专知www.zhuanzhi.ai,获取5000+AI主题干货知识资料!
欢迎微信扫一扫加入专知人工智能知识星球群,获取最新AI专业干货知识教程资料和与专家交流咨询
点击“ 阅读原文 ”,了解使用 专知 ,查看获取5000+AI主题知识资料
登录查看更多
15

相关内容

图机器学习(Machine Learning on Graphs)是一项重要且普遍存在的任务,其应用范围从药物设计到社交网络中的友情推荐。这个领域的主要挑战是找到一种表示或编码图结构的方法,以便机器学习模型能够轻松地利用它。

知识荟萃

精品入门和进阶教程、论文和代码整理等

更多

查看相关VIP内容、论文、资讯等
2020图机器学习GNN的四大研究趋势,21篇论文下载
专知会员服务
135+阅读 · 2020年2月10日
AAAI2020接受论文列表,1591篇论文目录全集
专知会员服务
98+阅读 · 2020年1月12日
近期必读的5篇 CVPR 2019【图卷积网络】相关论文和代码
专知会员服务
32+阅读 · 2020年1月10日
【ICLR2020】五篇Open代码的GNN论文
专知会员服务
47+阅读 · 2019年10月2日
2020年,图机器学习将走向何方?
机器之心
5+阅读 · 2020年2月16日
NeurIPS2019机器学习顶会接受论文列表!
专知
28+阅读 · 2019年9月6日
自然语言处理顶会EMNLP2018接受论文列表!
专知
87+阅读 · 2018年8月26日
Arxiv
35+阅读 · 2020年1月2日
Deep Graph Infomax
Arxiv
17+阅读 · 2018年12月21日
Arxiv
7+阅读 · 2018年8月28日
VIP会员
相关VIP内容
2020图机器学习GNN的四大研究趋势,21篇论文下载
专知会员服务
135+阅读 · 2020年2月10日
AAAI2020接受论文列表,1591篇论文目录全集
专知会员服务
98+阅读 · 2020年1月12日
近期必读的5篇 CVPR 2019【图卷积网络】相关论文和代码
专知会员服务
32+阅读 · 2020年1月10日
【ICLR2020】五篇Open代码的GNN论文
专知会员服务
47+阅读 · 2019年10月2日
Top
微信扫码咨询专知VIP会员