图卷积网络(简称GCN),由Thomas Kpif于2017年在论文Semi-supervised classification with graph convolutional networks中提出。它为图(graph)结构数据的处理提供了一个崭新的思路,将深度学习中常用于图像的卷积神经网络应用到图数据上。

知识荟萃

图卷积神经网络 (GCN)荟萃

入门学习

  1. GCN 入门 https://www.cnblogs.com/megachen/p/11492647.html
  2. GCN入门理解 [https://blog.csdn.net/weixin_30468137/article/details/96697624]
  3. 从CNN到GCN的联系与区别——GCN从入门到精(fang)通(qi) [https://blog.csdn.net/weixin_40013463/article/details/81089223]
  4. GCN学习笔记 [https://www.cnblogs.com/ranup/p/10914494.html]
  5. [GCN] 论文笔记:SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS https://blog.csdn.net/qq_41727666/article/details/84640549

综述

  1. Relational inductive biases, deep learning, and graph networks Peter W. Battaglia [https://arxiv.org/pdf/1806.01261.pdf]
  2. Graph Neural Networks: A Review of Methods and Applications [https://arxiv.org/pdf/1812.08434v1.pdf]
  3. A Comprehensive Survey on Graph Neural Networks [https://arxiv.org/pdf/1901.00596.pdf]
  4. Deep Learning on Graphs: A Survey [https://arxiv.org/pdf/1812.04202.pdf]

进阶论文

2015

  1. David Duvenaud, Dougal Maclaurin, Jorge Aguilera-Iparraguirre, Rafael GómezBombarelli, Timothy Hirzel, Alán Aspuru-Guzik, Ryan P. Adams. Convolutional networks on graphs for learning molecular fingerprints [https://arxiv.org/pdf/1509.09292.pdf]

2016

  1. Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus. Learning Multiagent Communication with Backpropagation
    [https://arxiv.org/pdf/1605.07736.pdf]
  2. Ashesh Jain, Amir R. Zamir, Silvio Savarese, Ashutosh Saxena. Structural-RNN: Deep Learning on Spatio-Temporal Graphs
    [https://arxiv.org/abs/1511.05298]

2017

  1. Alex Fout, Jonathon Byrd, Basir Shariat, Asa Ben-Hur. Protein Interface Prediction using Graph Convolutional Networks
    [http://papers.nips.cc/paper/7231-protein-interface-prediction-using-graph-convolutional-networks.pdf]
  2. Daniel Oñoro-Rubio, Mathias Niepert, Alberto García-Durán, Roberto González, Roberto J. López-Sastre. Representation learning for visual-relational knowledge graphs
    [https://arxiv.org/pdf/1709.02314.pdf]
  3. Takuo Hamaguchi, Hidekazu Oiwa, Masashi Shimbo, Yuji Matsumoto. Knowledge Transfer for Out-of-Knowledge-Base Entities : A Graph Neural Network Approach
    [https://arxiv.org/pdf/1706.05674.pdf]
  4. Federico Monti, Michael M. Bronstein, Xavier Bresson. Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks
    [https://arxiv.org/abs/1704.06803]
  5. Rianne van den Berg, Thomas N. Kipf, Max Welling. Graph Convolutional Matrix Completion
    [https://arxiv.org/abs/1706.02263]
  6. Kenneth Marino, Ruslan Salakhutdinov, Abhinav Gupta. The More You Know: Using Knowledge Graphs for Image Classification
    [https://arxiv.org/pdf/1612.04844.pdf]
  7. Damien Teney, Lingqiao Liu, Anton van den Hengel. Graph-Structured Representations for Visual Question Answering
    [https://arxiv.org/pdf/1609.05600.pdf]
  8. Xiaojuan Qi, Renjie Liao, Jiaya Jia, Sanja Fidler, Raquel Urtasun. 3D Graph Neural Networks for RGBD Semantic Segmentation
    [https://ieeexplore.ieee.org/document/8237818]
  9. Martin Simonovsky, Nikos Komodakis. Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
    [https://arxiv.org/pdf/1704.02901.pdf]
  10. Ruiyu Li, Makarand Tapaswi, Renjie Liao, Jiaya Jia, Raquel Urtasun, Sanja Fidler. Situation Recognition with Graph Neural Networks
    [https://arxiv.org/pdf/1708.04320.pdf]
  11. Diego Marcheggiani, Ivan Titov. Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
    [https://arxiv.org/abs/1703.04826]
  12. Joost Bastings, Ivan Titov, Wilker Aziz, Diego Marcheggiani, Khalil Sima'an. Graph Convolutional Encoders for Syntax-aware Neural Machine Translation
    [https://arxiv.org/pdf/1704.04675.pdf]

2018

  1. Thomas Kipf, Ethan Fetaya, Kuan-Chieh Wang, Max Welling, Richard Zemel. Neural Relational Inference for Interacting Systems
    [https://arxiv.org/pdf/1802.04687.pdf]
  2. Marinka Zitnik, Monica Agrawal, Jure Leskovec. Modeling polypharmacy side effects with graph convolutional networks
    [https://arxiv.org/abs/1802.00543.pdf]
  3. Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, Max Welling. Modeling Relational Data with Graph Convolutional Networks
    [https://arxiv.org/pdf/1703.06103.pdf]
  4. Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L. Hamilton, Jure Leskovec. Graph Convolutional Neural Networks for Web-Scale Recommender Systems
    [https://arxiv.org/abs/1806.01973.pdf]
  5. Medhini Narasimhan, Svetlana Lazebnik, Alexander Schwing. Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
    [https://arxiv.org/abs/1811.00538]
  6. Han Hu, Jiayuan Gu, Zheng Zhang, Jifeng Dai, Yichen Wei. Relation Networks for Object Detection
    [https://arxiv.org/abs/1711.11575]
  7. DSijie Yan, Yuanjun Xiong, Dahua Lin. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
    [https://arxiv.org/pdf/1801.07455.pdf]
  8. Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon. Dynamic Graph CNN for Learning on Point Clouds
    [https://arxiv.org/pdf/1801.07829.pdf]
  9. Charles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
    [https://arxiv.org/pdf/1612.00593.pdf]
  10. Zhouxia Wang, Tianshui Chen, Jimmy Ren, Weihao Yu, Hui Cheng, Liang Lin. Deep Reasoning with Knowledge Graph for Social Relationship Understanding
    [https://arxiv.org/pdf/1807.00504.pdf]
  11. Thien Huu Nguyen, Ralph Grishman. Graph Convolutional Networks with Argument-Aware Pooling for Event Detection
    [http://ix.cs.uoregon.edu/~thien/pubs/graphConv.pdf]
  12. Diego Marcheggiani, Joost Bastings, Ivan Titov. Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks
    [https://www.aclweb.org/anthology/N18-2078/]
  13. Linfeng Song, Zhiguo Wang, Mo Yu, Yue Zhang, Radu Florian, Daniel Gildea. Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks
    [https://arxiv.org/abs/1809.02040]
  14. Yuhao Zhang, Peng Qi, Christopher D. Manning. Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
    [https://arxiv.org/abs/1809.10185]
  15. Daniel Beck, Gholamreza Haffari, Trevor Cohn. Graph-to-Sequence Learning using Gated Graph Neural Networks
    [https://arxiv.org/pdf/1806.09835.pdf]
  16. Afshin Rahimi, Trevor Cohn, Timothy Baldwin. Semi-supervised User Geolocation via Graph Convolutional Networks
    [https://arxiv.org/pdf/1804.08049.pdf]
  17. Daniil Sorokin, Iryna Gurevych. Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering
    [https://arxiv.org/pdf/1808.04126.pdf]

2019

  1. Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola. Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
    [https://openreview.net/pdf?id=B1xJAsA5F7]
  2. Peifeng Wang, Jialong Han, Chenliang Li, Rong Pan. Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding
    [https://arxiv.org/pdf/1811.01399.pdf]
  3. Namyong Park, Andrey Kan, Xin Luna Dong, Tong Zhao, Christos Faloutsos. Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks
    [https://arxiv.org/pdf/1905.08865.pdf]
  4. Deepak Nathani, Jatin Chauhan, Charu Sharma, Manohar Kaul. Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs
    [https://arxiv.org/pdf/1906.01195.pdf]
  5. Kun Xu, Mo Yu, Yansong Feng, Yan Song, Zhiguo Wang, Dong Yu. Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
    [https://128.84.21.199/pdf/1905.11605.pdf]
  6. Jiani Zhang, Xingjian Shi, Shenglin Zhao, Irwin King. STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
    [https://arxiv.org/pdf/1905.13129.pdf]
  7. Haoyu Wang, Defu Lian, Yong Ge. Binarized Collaborative Filtering with Distilling Graph Convolutional Networks
    [https://arxiv.org/pdf/1906.01829.pdf]
  8. Shu Wu, Yuyuan Tang, Yanqiao Zhu, Liang Wang, Xing Xie, Tieniu Tan. Session-based Recommendation with Graph Neural Networks
    [https://arxiv.org/pdf/1811.00855.pdf]
  9. Jin Shang, Mingxuan Sun. Geometric Hawkes Processes with Graph Convolutional Recurrent Neural Networks
    [https://jshang2.github.io/pubs/geo.pdf]
  10. Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, Tat-Seng Chua. KGAT: Knowledge Graph Attention Network for Recommendation
    [https://arxiv.org/pdf/1905.07854.pdf]
  11. Hongwei Wang, Miao Zhao, Xing Xie, Wenjie Li, Minyi Guo. Knowledge Graph Convolutional Networks for Recommender Systems
    [https://arxiv.org/pdf/1904.12575.pdf]
  12. Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, Dawei Yin. Graph Neural Networks for Social Recommendation
    [https://arxiv.org/pdf/1902.07243.pdf]
  13. Junyu Gao, Tianzhu Zhang, Changsheng Xu. I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs
    [https://aaai.org/ojs/index.php/AAAI/article/view/4843]
  14. Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, Yanwen Guo. Multi-Label Image Recognition with Graph Convolutional Networks
    [https://arxiv.org/pdf/1904.03582.pdf]
  15. Xinhong Ma, Tianzhu Zhang, Changsheng Xu. GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation
    [http://openaccess.thecvf.com/content_CVPR_2019/papers/Ma_GCAN_Graph_Convolutional_Adversarial_Network_for_Unsupervised_Domain_Adaptation_CVPR_2019_paper.pdf]
  16. Mengshi Qi, Weijian Li, Zhengyuan Yang, Yunhong Wang, Jiebo Luo. Attentive Relational Networks for Mapping Images to Scene Graphs
    [https://arxiv.org/pdf/1811.10696.pdf]
  17. Jianchao Wu, Limin Wang, Li Wang, Jie Guo, Gangshan Wu. Learning Actor Relation Graphs for Group Activity Recognition
    [https://arxiv.org/pdf/1904.10117.pdf]
  18. Yunpeng Chen, Marcus Rohrbach, Zhicheng Yan, Shuicheng Yan, Jiashi Feng, Yannis Kalantidis. Graph-Based Global Reasoning Networks
    [https://arxiv.org/pdf/1811.12814.pdf]
  19. Zhongdao Wang, Liang Zheng, Yali Li, Shengjin Wang. Linkage Based Face Clustering via Graph Convolution Network
    [https://arxiv.org/pdf/1903.11306.pdf]
  20. Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris N. Metaxas. Semantic Graph Convolutional Networks for 3D Human Pose Regression
    [https://arxiv.org/pdf/1904.03345.pdf]
  21. Yichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang. Learning Context Graph for Person Search
    [https://arxiv.org/pdf/1904.01830.pdf]
  22. Lei Wang, Yuchun Huang, Yaolin Hou, Shenman Zhang, Jie Shan. Graph Attention Convolution for Point Cloud Semantic Segmentation
    [http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Graph_Attention_Convolution_for_Point_Cloud_Semantic_Segmentation_CVPR_2019_paper.pdf]
  23. Maosen Li, Siheng Chen, Xu Chen, Ya Zhang, Yanfeng Wang, Qi Tian. Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
    [https://arxiv.org/pdf/1904.12659.pdf]
  24. Junyu Gao, Tianzhu Zhang, Changsheng Xu. Graph Convolutional Tracking
    [http://nlpr-web.ia.ac.cn/mmc/homepage/jygao/JY_Gao_files/Conference_Papers/GCT-CVPR2019-GJY.pdf]
  25. Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu. Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
    [http://openaccess.thecvf.com/content_CVPR_2019/papers/Shi_Two-Stream_Adaptive_Graph_Convolutional_Networks_for_Skeleton-Based_Action_Recognition_CVPR_2019_paper.pdf]
  26. Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu. Skeleton-Based Action Recognition With Directed Graph Neural Networks
    [http://openaccess.thecvf.com/content_CVPR_2019/papers/Shi_Skeleton-Based_Action_Recognition_With_Directed_Graph_Neural_Networks_CVPR_2019_paper.pdf]
  27. Liang Yao, Chengsheng Mao, Yuan Luo. Graph Convolutional Networks for Text Classification
    [https://arxiv.org/pdf/1809.05679.pdf]
  28. Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, Partha Talukdar Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
    [https://arxiv.org/pdf/1809.04283.pdf]
  29. Sunil Kumar Sahu, Fenia Christopoulou, Makoto Miwa, Sophia Ananiadou. Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network
    [https://arxiv.org/pdf/1906.04684.pdf]
  30. Daesik Kim, Seonhoon Kim, Nojun Kwak. Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension
    [https://arxiv.org/pdf/1811.00232.pdf]
  31. Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei Li, Weinan Zhang, Yong Yu. Dynamically Fused Graph Network for Multi-hop Reasoning
    [https://arxiv.org/pdf/1905.06933.pdf]
  32. Zhijiang Guo, Yan Zhang, Wei Lu. Attention Guided Graph Convolutional Networks for Relation Extraction
    [http://www.statnlp.org/wp-content/uploads/2019/06/Attention_Guided_Graph_Convolutional_Networks_for_Relation_Extraction.pdf]
  33. Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-seng Chua, Maosong Sun. Graph Neural Networks with Generated Parameters for Relation Extraction
    [https://arxiv.org/pdf/1902.00756.pdf]
  34. Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang, Huajun Chen. Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks
    [https://arxiv.org/pdf/1903.01306.pdf]
  35. Chun Wang, Shirui Pan, Ruiqi Hu, Guodong Long, Jing Jiang, Chengqi Zhang. Attributed Graph Clustering: A Deep Attentional Embedding Approach
    [https://arxiv.org/pdf/1906.06532.pdf]
  36. Xiaotong Zhang, Han Liu, Qimai Li, Xiao-Ming Wu. Attributed Graph Clustering via Adaptive Graph Convolution
    [https://arxiv.org/pdf/1906.01210.pdf]
  37. Jia Li, Yu Rong, Hong Cheng, Helen Meng, Wenbing Huang, Junzhou Huang. Semi-Supervised Graph Classification: A Hierarchical Graph Perspective
    [https://arxiv.org/pdf/1904.05003.pdf]
  38. Hao Wang, Tong Xu, Qi Liu, Defu Lian, Enhong Chen, Dongfang Du, Han Wu, Wen Su. MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network
    [https://arxiv.org/pdf/1905.11013.pdf]
  39. Ninghao Liu, Qiaoyu Tan, Yuening Li, Hongxia Yang, Jingren Zhou, Xia Hu. Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
    [https://arxiv.org/pdf/1905.10668.pdf]
  40. Chang Li, Dan Goldwasser. Encoding Social Information with Graph Convolutional Networks for Political Perspective Detection in News Media [https://www.cs.purdue.edu/homes/dgoldwas//downloads/papers/LiG_acl_2019.pdf]
  41. Hao Peng, Jianxin Li, Qiran Gong, Yangqiu Song, Yuanxing Ning, Kunfeng Lai, Philip S. Yu. Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks
    [https://arxiv.org/pdf/1906.04580.pdf]

Tutorial

  1. AAAI2019 Tutorial 《图表示学习》, 180页PPT带你从入门到精通 [https://www.zhuanzhi.ai/document/91ad3a1b183061fc8cca79b20b7d0e58]
  2. Graph Convolutional Neural Networks [https://github.com/dbusbridge/gcn_tutorial]
  3. 洛桑理工27页PPT带你入坑GCN:Graph上的深度学习报告 [https://mp.weixin.qq.com/s?src=11&timestamp=1575874094&ver=2023&signature=9LcXP6hPe0E4kcqXSwrO5P3AoVj4Snzqsic-wJm7dd9FwRiGZuS0uK12Mi4RQBTu4fqag1W4LVGDdRsVEn4eqOAJe0-SA7Ey2LlSq-XPEn8KGQIZsBW9PF*axzDhPS&new=1]

视频教程

  1. KDD 2019 Graph Convolutional Networks with EigenPooling [https://www.kdd.org/kdd2019/accepted-papers/view/graph-convolutional-networks-with-eigenpooling]
  2. 图卷积介绍
    [https://www.youtube.com/watch?v=UAwrDY_Bcdc]
  3. Graph Convolutional Neural Networks [https://www.youtube.com/watch?v=Mf-mIRF3ao8]
  4. Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning
    [http://primo.ai/index.php?title=Graph_Convolutional_Network_(GCN),Graph_Neural_Networks(Graph_Nets),_Geometric_Deep_Learning]
  5. Convolutional Neural Networks on Graphs [https://www.youtube.com/watch?v=v3jZRkvIOIM]

代码

  1. 使用DGL实现图卷积网络 [https://docs.dgl.ai/en/latest/tutorials/models/1_gnn/1_gcn.html]
  2. pointnet代码 [https://github.com/charlesq34/pointnet]
  3. pointnet++代码 [https://github.com/charlesq34/pointnet2]
  4. pytorch实现GCN [https://github.com/tkipf/pygcn]
  5. tensorflow 实现GCN [https://github.com/tkipf/gcn]
  6. Deep Learning on Graphs with Keras [https://github.com/tkipf/keras-gcn]

领域专家

  1. University of Amsterdam: Thomas Kipf
  2. TU Dortmund University - Interested in Representation Learning on Graphs and Manifolds; PyTorch, CUDA, Vim and macOS Enthusiast: Matthias Fey
  3. School of Computer Science and Engineering, Nanyang Technological University: Xavier Bresson
  4. Department of Computer Science, Stanford University: Jure Leskovec
  5. Stanford University: Zhitao Ying
  6. 北京大学数学科学学院: 朱占星

VIP内容

近年来,围绕着图卷积网络(GCN)这一主题的文献大量涌现。如何有效地利用复杂图(如具有异构实体和关系类型的知识图谱)中丰富的结构信息是该领域面临的主要挑战。大多数GCN方法要么局限于具有同质边类型的图(例如,仅引用链接),要么只专注于节点的表示学习,而不是针对目标驱动的目标共同传播和更新节点和边的嵌入。本文提出了一种新的框架,即基于知识嵌入的图卷积网络(KE-GCN),该框架结合了基于图的信念传播中知识嵌入的能力和高级知识嵌入(又称知识图嵌入)方法的优势,从而解决了这些局限性。我们的理论分析表明,KE-GCN作为具体案例提供了几种著名的GCN方法的优雅统一,并提供了图卷积的新视角。在基准数据集上的实验结果表明,与强基线方法相比,KE-GCN方法在知识图谱对齐和实体分类等任务中具有明显的优势。

https://www.zhuanzhi.ai/paper/3404ccd79333da7c1cbf8e013f258a64

成为VIP会员查看完整内容
0
23

最新论文

The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition require cooperative gait scenarios, in which a single person is walking multiple times in a straight line in front of a camera. We aim to address the hard challenges of real-world scenarios in which camera feeds capture multiple people, who in most cases pass in front of the camera only once. We address privacy concerns by using only motion information of walking individuals, with no identifiable appearance-based information. As such, we propose a novel weakly supervised learning framework, WildGait, which consists of training a Spatio-Temporal Graph Convolutional Network on a large number of automatically annotated skeleton sequences obtained from raw, real-world, surveillance streams to learn useful gait signatures. Our results show that, with fine-tuning, we surpass in terms of recognition accuracy the current state-of-the-art pose-based gait recognition solutions. Our proposed method is reliable in training gait recognition methods in unconstrained environments, especially in settings with scarce amounts of annotated data. We obtain an accuracy of 84.43% on CASIA-B and 71.3% on FVG, while using only 10% of the available training data. This consists of 29% and 38% accuracy improvement on the respective datasets when using the same network without pretraining.

0
0
下载
预览
Top