{"type":"ScholarlyArticle","title":"RAW-GNN: RAndom Walk Aggregation based Graph Neural Network","authors":[{"name":"Di Jin","slug":"di-jin","given":"Di","family":"Jin","affiliation":"College of Intelligence and Computing , Tianjin University , Tianjin , China"},{"name":"Rui Wang","slug":"rui-wang","given":"Rui","family":"Wang","affiliation":"College of Intelligence and Computing , Tianjin University , Tianjin , China"},{"name":"Meng Ge","slug":"meng-ge","given":"Meng","family":"Ge","affiliation":"College of Intelligence and Computing , Tianjin University , Tianjin , China"},{"name":"Dongxiao He","slug":"dongxiao-he","given":"Dongxiao","family":"He","affiliation":"College of Intelligence and Computing , Tianjin University , Tianjin , China"},{"name":"Xiang Li","slug":"xiang-li","given":"Xiang","family":"Li","affiliation":"Meituan , Beijing , China"},{"name":"Wei Lin","slug":"wei-lin","given":"Wei","family":"Lin","affiliation":"Meituan , Beijing , China"},{"name":"Weixiong Zhang","slug":"weixiong-zhang","given":"Weixiong","family":"Zhang","affiliation":"Department of Health Technology and Informatics , The Hong Kong Polytechnic University , Kowloon , Hong Kong"}],"abstract":"Graph-Convolution-based methods have been successfully applied to representation learning on homophily graphs where nodes with the same label or similar attributes tend to connect with one another. Due to the homophily assumption of Graph Convolutional Networks (GCNs) that these methods use, they are not suitable for heterophily graphs where nodes with different labels or dissimilar attributes tend to be adjacent. Several methods have attempted to address this heterophily problem, but they do not change the fundamental aggregation mechanism of GCNs because they rely on summation operators to aggregate information from neighboring nodes, which is implicitly subject to the homophily assumption. Here, we introduce a novel aggregation mechanism and develop a RAndom Walk Aggregation-based Graph Neural Network (called RAW-GNN) method. The proposed approach integrates the random walk strategy with graph neural networks. The new method utilizes breadth-first random walk search to capture homophily information and depth-first search to collect heterophily information. It replaces the conventional neighborhoods with path-based neighborhoods and introduces a new path-based aggregator based on Recurrent Neural Networks. These designs make RAW-GNN suitable for both homophily and heterophily graphs. Extensive experimental results showed that the new method achieved state-of-the-art performance on a variety of homophily and heterophily graphs.","doi":"10.24963/ijcai.2022/293","url":"https://ijcai.org/proceedings/2022/293","pdf":"https://ijcai.org/proceedings/2022/0293.pdf","markdown":"https://ijcai.org/proceedings/2022/293.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/293","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Data Mining","track":"Main Track","number":293,"pages":{"first":2108,"last":2114},"keywords":["Data Mining: Mining Graphs","Machine Learning: Sequence and Graph Learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987027","length_sec":101,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985170","length_sec":613,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chien et al., 2021] Eli Chien, Jianhao Peng, Pan Li, and Ol- gica Milenkovic. Adaptive universal generalized pagerank graph neural network. In Proceeding of the 9th Interna- tional Conference on Learning Representations, 2021.","title":"Adaptive universal generalized pagerank graph neural network","authors":"Eli Chien, Jianhao Peng, Pan Li, Olgica Milenkovic","year":"2021","venue":"Proceeding of the 9th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart van Merrienboer, C ¸aglar Gülc ¸ehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the 2014 Confer- ence on Empirical Methods in Natural Language Process- ing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1724-1734, 2014.","title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Du et al., 2021] Zhengxiao Du, Chang Zhou, Jiangchao Yao, Teng Tu, Letian Cheng, Hongxia Yang, Jingren Zhou, and Jie Tang. Cogkr: Cognitive graph for multi-hop knowledge reasoning. IEEE Transactions on Knowledge and Data Engineering, 2021.","title":"Cogkr: Cognitive graph for multi-hop knowledge reasoning","authors":"Zhengxiao Du, Chang Zhou, Jiangchao Yao, Teng Tu, Letian Cheng, Hongxia Yang, Jingren Zhou, Jie Tang","year":"2021","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fu et al., 2020] Xinyu Fu, Jiani Zhang, Ziqiao Meng, and Irwin King. MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding. In WWW '20: The Web Conference 2020, Taipei, Taiwan, April 20- 24, 2020, pages 2331-2341, 2020.","title":"MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding","authors":"Xinyu Fu, Jiani Zhang, Ziqiao Meng, Irwin King","year":"2020","venue":"WWW '20: The Web Conference 2020","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Grover and Leskovec, 2016] Aditya Grover and Jure Leskovec. Node2vec: scalable feature learning for networks. In Proceedings of the 22th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 855-864. ACM, 2016.","title":"Node2vec: scalable feature learning for networks","authors":"Leskovec Grover, Aditya Grover, Jure Leskovec","year":"2016","venue":"Proceedings of the 22th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hamilton et al., 2017] William L. Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In Advances in Neural Information Process- ing Systems 30, pages 1024-1034, 2017.","title":"Inductive representation learning on large graphs","authors":"William L Hamilton, Zhitao Ying, Jure Leskovec","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2022] Dongxiao He, Chundong Liang, Huixin Liu, Mingxiang Wen, Pengfei Jiao, and Zhiyong Feng. Block modeling-guided graph convolutional neural net- works. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022.","title":"Block modeling-guided graph convolutional neural networks","authors":"Dongxiao He, Chundong Liang, Huixin Liu, Mingxiang Wen, Pengfei Jiao, Zhiyong Feng","year":"2022","venue":"Proceedings of the 36th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jin et al., 2021] Di Jin, Cuiying Huo, Chundong Liang, and Liang Yang. Heterogeneous graph neural network via at- tribute completion. In Proceedings of the Web Conference 2021, pages 391-400, 2021.","title":"Heterogeneous graph neural network via attribute completion","authors":"Di Jin, Cuiying Huo, Chundong Liang, Liang Yang","year":"2021","venue":"Proceedings of the Web Conference 2021","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kipf and Welling, 2017] Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In Proceeding of the 5th International Confer- ence on Learning Representations, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"Thomas N Kipf, Max Welling","year":"2017","venue":"Proceeding of the 5th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lim et al., 2021] Derek Lim, Felix Hohne, Xiuyu Li, Si- jia Linda Huang, Vaishnavi Gupta, Omkar Bhalerao, and Ser Nam Lim. Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods. In Advances in Neural Information Processing Systems, vol- ume 34, pages 20887-20902, 2021.","title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods","authors":"Derek Lim, Felix Hohne, Xiuyu Li, Linda Sijia, Vaishnavi Huang, Omkar Gupta, Bhalerao, Nam Ser, Lim","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[LJPvd and Hinton, 2008] Maaten LJPvd and GE Hinton. Visualizing high-dimensional data using t-sne. J Mach Learn Res, 9(2579-2605):9, 2008.","title":"Visualizing high-dimensional data using t-sne","authors":"Maaten Ljpvd, Hinton","year":"2008","venue":"J Mach Learn Res","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Namata et al., 2012] Galileo Mark Namata, Ben London, Lise Getoor, and Bert Huang. Query-driven active survey- ing for collective classification. In Workshop on Mining and Learning with Graphs (MLG), 2012.","title":"Query-driven active surveying for collective classification","authors":"Namata","year":"2012","venue":"Workshop on Mining and Learning with Graphs (MLG)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Pei et al., 2020] Hongbin Pei, Bingzhe Wei, Kevin Chen- Chuan Chang, Yu Lei, and Bo Yang. Geom-gcn: Geo- metric graph convolutional networks. In Proceeding of the 8th International Conference on Learning Represen- tations, 2020.","title":"Geom-gcn: Geometric graph convolutional networks","authors":"Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan, Yu Chang, Bo Lei, Yang","year":"2020","venue":"Proceeding of the 8th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Sen et al., 2008] Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Gallagher, and Tina Eliassi- Rad. Collective classification in network data. AI Mag- azine., 29(3):93-106, 2008.","title":"Collective classification in network data","authors":"Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Gallagher, Tina Eliassi-Rad","year":"2008","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Tang et al., 2009] Jie Tang, Jimeng Sun, Chi Wang, and Zi Yang. Social influence analysis in large-scale net- works. In Proceedings of the 15th ACM SIGKDD Interna- tional Conference on Knowledge Discovery & Data Min- ing, pages 807-816, 2009.","title":"Social influence analysis in large-scale networks","authors":"Jie Tang, Jimeng Sun, Chi Wang, Zi Yang","year":"2009","venue":"Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wang et al., 2016] Zheng Wang, Chaokun Wang, Jisheng Pei, Xiaojun Ye, and Philip S. Yu. Causality based propa- gation history ranking in social networks. In Proceedings of the 25th International Joint Conference on Artificial In- telligence, pages 3917-3923, 2016.","title":"Causality based propagation history ranking in social networks","authors":"Zheng Wang, Chaokun Wang, Jisheng Pei, Xiaojun Ye, Philip S Yu","year":"2016","venue":"Proceedings of the 25th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/551"},{"position":17,"raw":"[Wang et al., 2022] Tao Wang, Di Jin, Rui Wang, Dongx- iao He, and Yuxiao Huang. Powerful graph convolutioal networks with adaptive propagation mechanism for ho- mophily and heterophily. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022.","title":"Powerful graph convolutioal networks with adaptive propagation mechanism for homophily and heterophily","authors":"Tao Wang, Di Jin, Rui Wang, Dongxiao He, Yuxiao Huang","year":"2022","venue":"Proceedings of the 36th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Yan et al., 2021] Yujun Yan, Milad Hashemi, Kevin Swer- sky, Yaoqing Yang, and Danai Koutra. Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks. arXiv preprint arXiv:2102.06462, 2021.","title":"Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks","authors":"Yujun Yan, Milad Hashemi, Kevin Swersky, Yaoqing Yang, Danai Koutra","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yu et al., 2021] Zhizhi Yu, Di Jin, Ziyang Liu, Dongxiao He, Xiao Wang, Hanghang Tong, and Jiawei Han. As- gcn: Adaptive semantic architecture of graph convolu- tional networks for text-rich networks. In 2021 IEEE Inter- national Conference on Data Mining (ICDM), pages 837- 846. IEEE, 2021.","title":"Asgcn: Adaptive semantic architecture of graph convolutional networks for text-rich networks","authors":"Zhizhi Yu, Di Jin, Ziyang Liu, Dongxiao He, Xiao Wang, Hanghang Tong, Jiawei Han","year":"2021","venue":"IEEE International Conference on Data Mining (ICDM)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhu et al., 2020] Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. Be- yond homophily in graph neural networks: Current limita- tions and effective designs. In Advances in Neural Infor- mation Processing Systems 33, 2020.","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","authors":"Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, Danai Koutra","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhu et al., 2021a] Jiong Zhu, Ryan A. Rossi, Anup B. Rao, Tung Mai, Nedim Lipka, Nesreen K. Ahmed, and Danai Koutra. Graph neural networks with heterophily. In Pro- ceedings of the 35th AAAI Conference on Artificial Intelli- gence, 2021.","title":"Graph neural networks with heterophily","authors":"Zhu","year":"2021","venue":"Proceedings of the 35th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhu et al., 2021b] Meiqi Zhu, Xiao Wang, Chuan Shi, Houye Ji, and Peng Cui. Interpreting and unifying graph neural networks with an optimization framework. In WWW '21: The Web Conference 2021, pages 1215-1226, 2021.","title":"Interpreting and unifying graph neural networks with an optimization framework","authors":"Zhu","year":"2021","venue":"WWW '21: The Web Conference 2021","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}