{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T23:05:01Z","timestamp":1782169501016,"version":"3.54.5"},"reference-count":33,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T00:00:00Z","timestamp":1693958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62276099"],"award-info":[{"award-number":["62276099"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"SWPU Innovation Base No. 642"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2024,1,31]]},"abstract":"<jats:p>Graph representation learning aims at integrating node contents with graph structure to learn nodes\/graph representations. Nevertheless, it is found that many existing graph learning methods do not work well on data with high heterophily level that accounts for a large proportion of edges between different class labels. Recent efforts to this problem focus on improving the message passing mechanism. However, it remains unclear whether heterophily truly does harm to the performance of graph neural networks (GNNs). The key is to unfold the relationship between a node and its immediate neighbors, e.g., are they heterophilous or homophilious? From this perspective, here we study the role of heterophily in graph representation learning before\/after the relationships between connected nodes are disclosed. In particular, we propose an end-to-end framework that both learns the type of edges (i.e., heterophilous\/homophilious) and leverage edge type information to improve the expressiveness of graph neural networks. We implement this framework in two different ways. Specifically, to avoid messages passing through heterophilous edges, we can optimize the graph structure to be homophilious by dropping heterophilous edges identified by an edge classifier. Alternatively, it is possible to exploit the information about the presence of heterophilous neighbors for feature learning, so a hybrid message passing approach is devised to aggregate homophilious neighbors and diversify heterophilous neighbors based on edge classification. Extensive experiments demonstrate the remarkable performance improvement of GNNs with the proposed framework on multiple datasets across the full spectrum of homophily level.<\/jats:p>\n          <jats:p\/>","DOI":"10.1145\/3603378","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T11:34:41Z","timestamp":1685705681000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Revisiting the Role of Heterophily in Graph Representation Learning: An Edge Classification Perspective"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8181-9410","authenticated-orcid":false,"given":"Jincheng","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8391-6510","authenticated-orcid":false,"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9305-2915","authenticated-orcid":false,"given":"Rui","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1085-3727","authenticated-orcid":false,"given":"Na","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6654-8664","authenticated-orcid":false,"given":"Acong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,9,6]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"21","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Abu-El-Haija Sami","year":"2019","unstructured":"Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, and Aram Galstyan. 2019. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In Proceedings of the International Conference on Machine Learning. PMLR, 21\u201329."},{"key":"e_1_3_2_3_2","first-page":"3950","volume-title":"Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021, 33rd Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The 11th Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2\u20139, 2021","author":"Bo Deyu","unstructured":"Deyu Bo, Xiao Wang, Chuan Shi, and Huawei Shen. 2021. Beyond low-frequency information in graph convolutional networks. In Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021, 33rd Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The 11th Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2\u20139, 2021. AAAI,3950\u20133957."},{"key":"e_1_3_2_4_2","volume-title":"Proceedings of the 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","author":"Chien Eli","unstructured":"Eli Chien, Jianhao Peng, Pan Li, and Olgica Milenkovic. 2021. Adaptive universal generalized PageRank graph neural network. In Proceedings of the 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC04228D"},{"key":"e_1_3_2_6_2","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"Defferrard Micha\u00ebl","year":"2016","unstructured":"Micha\u00ebl Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in Neural Information Processing Systems 29 (2016), 3844\u20133852.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512201"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.2200\/S01045ED1V01Y202009AIM046"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294869"},{"key":"e_1_3_2_10_2","volume-title":"Proceedings of the 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","author":"Hou Yifan","unstructured":"Yifan Hou, Jian Zhang, James Cheng, Kaili Ma, Richard T. B. Ma, Hongzhi Chen, and Ming-Chang Yang. [n. d.]. Measuring and improving the use of graph information in graph neural networks. In Proceedings of the 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020."},{"key":"e_1_3_2_11_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings","author":"Jang Eric","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. [n. d.]. Categorical reparameterization with gumbel-softmax. In Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_12_2","first-page":"2607","volume-title":"Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA","author":"Jin Wengong","unstructured":"Wengong Jin, Connor W. Coley, Regina Barzilay, and Tommi S. Jaakkola. [n. d.]. Predicting organic reaction outcomes with weisfeiler-lehman network. In Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA. 2607\u20132616."},{"key":"e_1_3_2_13_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kim Dongkwan","year":"2020","unstructured":"Dongkwan Kim and Alice Oh. 2020. How to find your friendly neighborhood: Graph attention design with self-supervision. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_14_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings."},{"key":"e_1_3_2_15_2","unstructured":"Derek Lim Felix Hohne Xiuyu Li Sijia Linda Huang Vaishnavi Gupta Omkar Bhalerao and Ser Nam Lim. 2021. Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods. Advances in Neural Information Processing Systems 34 (2021) 20887\u201320902."},{"key":"e_1_3_2_16_2","unstructured":"Sitao Luan Chenqing Hua Qincheng Lu Jiaqi Zhu Mingde Zhao Shuyuan Zhang Xiao-Wen Chang and Doina Precup. 2021. Is heterophily a real nightmare for graph neural networks to do node classification? arXiv preprint arXiv:2109.05641 (2021)."},{"key":"e_1_3_2_17_2","unstructured":"Sitao Luan Mingde Zhao Chenqing Hua Xiao-Wen Chang and Doina Precup. 2020. Complete the missing half: Augmenting aggregation filtering with diversification for graph convolutional networks. arXiv:2008.08844. Retrieved from https:\/\/arxiv.org\/abs\/2008.08844."},{"key":"e_1_3_2_18_2","unstructured":"Hongbin Pei Bingzhe Wei Kevin Chen-Chuan Chang Yu Lei and Bo Yang. 2020. Geom-GCN: Geometric Graph Convolutional Networks. In 8th International Conference on Learning Representations ICLR 2020 Addis Ababa Ethiopia April 26-30 2020 ."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186005"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220077"},{"key":"e_1_3_2_21_2","first-page":"5241","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Qu Meng","year":"2019","unstructured":"Meng Qu, Yoshua Bengio, and Jian Tang. 2019. Gmnn: Graph markov neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 5241\u20135250."},{"key":"e_1_3_2_22_2","volume-title":"Proceedings of the 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","author":"Rong Yu","unstructured":"Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. [n. d.]. DropEdge: Towards deep graph convolutional networks on node classification. In Proceedings of the 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1093\/comnet\/cnab014"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557108"},{"key":"e_1_3_2_26_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_27_2","first-page":"6861","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Wu Felix","year":"2019","unstructured":"Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In Proceedings of the International Conference on Machine Learning. PMLR, 6861\u20136871."},{"key":"e_1_3_2_28_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, May 6\u20139, 2019","author":"Xu Keyulu","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How powerful are graph neural networks?. In Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, May 6\u20139, 2019. OpenReview.net."},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Yujun Yan Milad Hashemi Kevin Swersky Yaoqing Yang and Danai Koutra. 2021. Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks. arXiv:2102.06462. Retrieved from https:\/\/arxiv.org\/abs\/2102.06462.","DOI":"10.1109\/ICDM54844.2022.00169"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Jianwei Yang Jiasen Lu Stefan Lee Dhruv Batra and Devi Parikh. 2018. Graph r-cnn for scene graph generation. In Proceedings of the European Conference on Computer Vision (ECCV\u201918) . 670\u2013685.","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"e_1_3_2_31_2","first-page":"40","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Yang Zhilin","year":"2016","unstructured":"Zhilin Yang, William Cohen, and Ruslan Salakhudinov. 2016. Revisiting semi-supervised learning with graph embeddings. In Proceedings of the International Conference on Machine Learning. PMLR, 40\u201348."},{"key":"e_1_3_2_32_2","first-page":"11458","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Zheng Cheng","year":"2020","unstructured":"Cheng Zheng, Bo Zong, Wei Cheng, Dongjin Song, Jingchao Ni, Wenchao Yu, Haifeng Chen, and Wei Wang. 2020. Robust graph representation learning via neural sparsification. In Proceedings of the International Conference on Machine Learning. PMLR, 11458\u201311468."},{"key":"e_1_3_2_33_2","first-page":"11168","volume-title":"Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021, 33rd Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The 11th Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2\u20139, 2021","author":"Zhu Jiong","unstructured":"Jiong Zhu, Ryan A. Rossi, Anup Rao, Tung Mai, Nedim Lipka, Nesreen K. Ahmed, and Danai Koutra. 2021. Graph neural networks with heterophily. In Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021, 33rd Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The 11th Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2\u20139, 2021. AAAI,11168\u201311176."},{"key":"e_1_3_2_34_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual","author":"Zhu Jiong","unstructured":"Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. 2020. Beyond homophily in graph neural networks: Current limitations and effective designs. In Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603378","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:25Z","timestamp":1750178785000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,6]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1,31]]}},"alternative-id":["10.1145\/3603378"],"URL":"https:\/\/doi.org\/10.1145\/3603378","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,6]]},"assertion":[{"value":"2022-06-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-30","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}