{"type":"ScholarlyArticle","title":"Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network","authors":[{"name":"Yifei Sun","slug":"yifei-sun","given":"Yifei","family":"Sun","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Haoran Deng","slug":"haoran-deng","given":"Haoran","family":"Deng","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Yang Yang","slug":"yang-yang","given":"Yang","family":"Yang","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Chunping Wang","slug":"chunping-wang","given":"Chunping","family":"Wang","affiliation":"Finvolution Group"},{"name":"Jiarong Xu","slug":"jiarong-xu","given":"Jiarong","family":"Xu","affiliation":"Department of Information Management and Business Intelligence , Fudan University"},{"name":"Renhong Huang","slug":"renhong-huang","given":"Renhong","family":"Huang","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Linfeng Cao","slug":"linfeng-cao","given":"Linfeng","family":"Cao","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Yang Wang","slug":"yang-wang","given":"Yang","family":"Wang","affiliation":"Finvolution Group"},{"name":"Lei Chen","slug":"lei-chen","given":"Lei","family":"Chen","affiliation":"Finvolution Group"}],"abstract":"Graph neural networks (GNNs) have been intensively studied in various real-world tasks. However, the homophily assumption of GNNs' aggregation function limits their representation learning ability in heterophily graphs. \r\nIn this paper, we shed light on the path level patterns in graphs that can explicitly reflect rich semantic and structural information.\r\nWe therefore propose a novel Structure-aware Path Aggregation Graph Neural Network (PathNet) aiming to generalize GNNs for both homophily and heterophily graphs. Specifically, we first introduce a maximal entropy path sampler, which helps us sample a number of paths containing structural context. Then, we introduce a structure-aware recurrent cell consisting of order-preserving and distance-aware components to learn the semantic information of neighborhoods. Finally, we model the preference of different paths to target node after path encoding.\r\nExperimental results demonstrate that our model achieves superior performance in node classification on both heterophily and homophily graphs.","doi":"10.24963/ijcai.2022/310","url":"https://ijcai.org/proceedings/2022/310","pdf":"https://ijcai.org/proceedings/2022/0310.pdf","markdown":"https://ijcai.org/proceedings/2022/310.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/310","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":310,"pages":{"first":2233,"last":2240},"keywords":["Data Mining: Mining Graphs"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986719","length_sec":86,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984862","length_sec":339,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Abu-El-Haija et al., 2019] Sami Abu-El-Haija, Bryan Per- ozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Ler- man, Hrayr Harutyunyan, Greg Ver Steeg, and Aram Gal- styan. MixHop: Higher-order graph convolutional archi- tectures via sparsified neighborhood mixing. In ICML, pages 21-29, 2019.","title":"MixHop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","authors":"Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bo et al., 2021] Deyu Bo, Xiao Wang, Chuan Shi, and Huawei Shen. Beyond low-frequency information in graph convolutional networks. In AAAI, pages 3950-3957, 2021.","title":"Beyond low-frequency information in graph convolutional networks","authors":"Deyu Bo, Xiao Wang, Chuan Shi, Huawei Shen","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Borgwardt et al., 2005] Karsten M Borgwardt, Cheng Soon Ong, Stefan Schönauer, SVN Vishwanathan, Alex J Smola, and Hans-Peter Kriegel. Protein function predic- tion via graph kernels. Bioinformatics, 21(suppl 1):47-56, 2005.","title":"Protein function prediction via graph kernels","authors":"Karsten M Borgwardt, Soon Cheng, Stefan Ong, Schönauer, Alex J Svn Vishwanathan, Hans-Peter Smola, Kriegel","year":"2005","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Burda et al., 2009] Zdzislaw Burda, Jarek Duda, Jean-Marc Luck, and Bartek Waclaw. Localization of the max- imal entropy random walk. Physical review letters, 102(16):160602, 2009.","title":"Localization of the maximal entropy random walk","authors":"Zdzislaw Burda, Jarek Duda, Jean-Marc Luck, Bartek Waclaw","year":"2009","venue":"Physical review letters","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2020] Zhengdao Chen, Lei Chen, Soledad Vil- lar, and Joan Bruna. Can graph neural networks count substructures? In NIPS, volume 33, pages 10383-10395, 2020.","title":"Can graph neural networks count substructures?","authors":"Chen","year":"2020","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2021] Lei Chen, Zhengdao Chen, and Joan Bruna. On graph neural networks versus graph-augmented mlps. In ICLR, 2021.","title":"On graph neural networks versus graph-augmented mlps","authors":"Lei Chen, Zhengdao Chen, Joan Bruna","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chien et al., 2021] Eli Chien, Jianhao Peng, Pan Li, and Ol- gica Milenkovic. Adaptive universal generalized pagerank graph neural network. In ICLR, 2021.","title":"Adaptive universal generalized pagerank graph neural network","authors":"Eli Chien, Jianhao Peng, Pan Li, Olgica Milenkovic","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. In EMNLP, pages 1724-1734, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"Thomas M Cover. Elements of information theory. John Wiley & Sons, 1999.","title":"Elements of information theory","authors":"M Thomas, Cover","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Dai and Wang, 2021] Enyan Dai and Suhang Wang. Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. In WSDM, pages 680-688, 2021.","title":"Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information","authors":"Wang ; ] Enyan Dai, Suhang Dai, Wang","year":"2021","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hamilton et al., 2017] William L Hamilton, Rex Ying, and Jure Leskovec. Inductive representation learning on large graphs. In NIPS, volume 30, pages 1025-1035, 2017.","title":"Inductive representation learning on large graphs","authors":"Rex William L Hamilton, Jure Ying, Leskovec","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hoeffding, 1963] Wassily Hoeffding. Probability inequali- ties for sums of bounded random variables. Journal of the American Statistical Association, 58(301):13-30, 1963.","title":"Wassily Hoeffding. Probability inequalities for sums of bounded random variables","authors":"Hoeffding","year":"1963","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kipf and Welling, 2017] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2019] Ziqi Liu, Chaochao Chen, Longfei Li, Jun Zhou, Xiaolong Li, Le Song, and Yuan Qi. Geniepath: Graph neural networks with adaptive receptive paths. In AAAI, pages 4424-4431, 2019.","title":"Geniepath: Graph neural networks with adaptive receptive paths","authors":"Ziqi Liu, Chaochao Chen, Longfei Li, Jun Zhou, Xiaolong Li, Le Song, Yuan Qi","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Luckie et al., 2013] Matthew Luckie, Bradley Huffaker, Amogh Dhamdhere, Vasileios Giotsas, et al. As relation- ships, customer cones, and validation. In IMC, pages 243- 256, 2013.","title":"As relationships, customer cones, and validation","authors":"Matthew Luckie, Bradley Huffaker, Amogh Dhamdhere, Vasileios Giotsas","year":"2013","venue":"IMC","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[McAuley et al., 2015] Julian McAuley, Rahul Pandey, and Jure Leskovec. Inferring networks of substitutable and complementary products. In SIGKDD, pages 785-794, 2015.","title":"Inferring networks of substitutable and complementary products","authors":"Julian Mcauley, Rahul Pandey, Jure Leskovec","year":"2015","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[McPherson et al., 2001] Miller McPherson, Lynn Smith- Lovin, and James M Cook. Birds of a feather: Homophily in social networks. Annual review of sociology, 27(1):415- 444, 2001.","title":"Birds of a feather: Homophily in social networks","authors":"Mcpherson","year":"2001","venue":"Annual review of sociology","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Newman, 2003] Mark EJ Newman. Mixing patterns in net- works. Physical review E, 67(2):026126, 2003.","title":"Mixing patterns in networks","authors":"Mark Ej Newman","year":"2003","venue":"Physical review E","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Parry, 1964] William Parry. Intrinsic markov chains. Trans- actions of the American Mathematical Society, 112(1):55- 66, 1964.","title":"Intrinsic markov chains","authors":"William Parry","year":"1964","venue":"Transactions of the American Mathematical Society","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rozemberczki et al., 2021] Benedek Rozemberczki, Carl Allen, and Rik Sarkar. Multi-Scale Attributed Node Em- bedding. Journal of Complex Networks, 9(2), 2021.","title":"Multi-Scale Attributed Node Embedding","authors":"Carl Benedek Rozemberczki, Rik Allen, Sarkar","year":"2021","venue":"Journal of Complex Networks","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Veličković et al., 2018] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. In ICLR, 2018.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2017] Boya Wu, Jia Jia, Yang Yang, Peijun Zhao, Jie Tang, and Qi Tian. Inferring emotional tags from social images with user demographics. IEEE Transactions on Multimedia, 19(7):1670-1684, 2017.","title":"Inferring emotional tags from social images with user demographics","authors":"Boya Wu, Jia Jia, Yang Yang, Peijun Zhao, Jie Tang, Qi Tian","year":"2017","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wu et al., 2020] Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S Yu Philip. A com- prehensive survey on graph neural networks. IEEE trans- actions on neural networks and learning systems, 32(1):4- 24, 2020.","title":"A comprehensive survey on graph neural networks","authors":"Wu","year":"2020","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xiong et al., 2019] Zhaoping Xiong, Dingyan Wang, Xi- aohong Liu, Feisheng Zhong, Xiaozhe Wan, Xutong Li, Zhaojun Li, Xiaomin Luo, Kaixian Chen, Hualiang Jiang, et al. Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism. Journal of medicinal chemistry, 63(16):8749-8760, 2019.","title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","authors":"Xiong","year":"2019","venue":"Journal of medicinal chemistry","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xu et al., 2019] Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural net- works? In ICLR, 2019.","title":"How powerful are graph neural networks?","authors":"Xu","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yang et al., 2018] Yang Yang, Zongtao Liu, Chenhao Tan, Fei Wu, Yueting Zhuang, and Yafeng Li. To stay or to leave: Churn prediction for urban migrants in the initial period. In WWW, pages 967-976, 2018.","title":"To stay or to leave: Churn prediction for urban migrants in the initial period","authors":"Yang Yang, Zongtao Liu, Chenhao Tan, Fei Wu, Yueting Zhuang, Yafeng Li","year":"2018","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yang et al., 2019a] Yang Yang, Yuhong Xu, Yizhou Sun, Yuxiao Dong, Fei Wu, and Yueting Zhuang. Mining fraud- sters and fraudulent strategies in large-scale mobile social networks. IEEE Transactions on Knowledge and Data En- gineering, 33(1):169-179, 2019.","title":"Mining fraudsters and fraudulent strategies in large-scale mobile social networks","authors":"Yang","year":"2019","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yang et al., 2019b] Yang Yang, Yuhong Xu, Chunping Wang, Yizhou Sun, Fei Wu, Yueting Zhuang, and Ming Gu. Understanding default behavior in online lending. In CIKM, pages 2043-2052, 2019.","title":"Understanding default behavior in online lending","authors":"Yang","year":"2019","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yang et al., 2019c] Yiding Yang, Xinchao Wang, Mingli Song, Junsong Yuan, and Dacheng Tao. Spagan: shortest path graph attention network. In IJCAI, pages 4099-4105, 2019.","title":"Spagan: shortest path graph attention network","authors":"Yang","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/569"},{"position":31,"raw":"[You et al., 2019] Jiaxuan You, Rex Ying, and Jure Leskovec. Position-aware graph neural networks. In ICML, pages 7134-7143. PMLR, 2019.","title":"Position-aware graph neural networks","authors":"You","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":32,"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 limi- tations and effective designs. In NIPS, volume 33, pages 7793-7804, 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":"NIPS","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}