{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T22:14:34Z","timestamp":1784585674465,"version":"3.55.0"},"reference-count":84,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["IIS-1707548 and IIS-1909702"],"award-info":[{"award-number":["IIS-1707548 and IIS-1909702"]}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"crossref","award":["W911NF21-1-0198"],"award-info":[{"award-number":["W911NF21-1-0198"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"crossref"}]},{"name":"DHS CINA","award":["E205949D"],"award-info":[{"award-number":["E205949D"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"<jats:p>\n            Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, such as nodes or edges, that the target GNN relies upon for making predictions. Though various algorithms are proposed, most of them formalize this task by searching the minimal subgraph, which can preserve original predictions. However, an inductive bias is deep-rooted in this framework: Several subgraphs can result in the same or similar outputs as the original graphs. Consequently, they have the danger of providing spurious explanations and failing to provide consistent explanations. Applying them to explain weakly performed GNNs would further amplify these issues. To address this problem, we theoretically examine the predictions of GNNs from the causality perspective. Two typical reasons for spurious explanations are identified: confounding effect of latent variables like distribution shift and causal factors distinct from the original input. Observing that both confounding effects and diverse causal rationales are encoded in internal representations,\n            <jats:styled-content style=\"color:#000000\">\n              we propose a new explanation framework with an auxiliary alignment loss, which is theoretically proven to be optimizing a more faithful explanation objective intrinsically. Concretely for this alignment loss, a set of different perspectives are explored: anchor-based alignment, distributional alignment based on Gaussian mixture models, mutual-information-based alignment, and so on. A comprehensive study is conducted both on the effectiveness of this new framework in terms of explanation faithfulness\/consistency and on the advantages of these variants. For our codes, please refer to the following URL link:\n              <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/TianxiangZhao\/GraphNNExplanation\">https:\/\/github.com\/TianxiangZhao\/GraphNNExplanation<\/jats:ext-link>\n            <\/jats:styled-content>\n          <\/jats:p>","DOI":"10.1145\/3616542","type":"journal-article","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T14:34:04Z","timestamp":1692801244000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4504-7809","authenticated-orcid":false,"given":"Tianxiang","family":"Zhao","sequence":"first","affiliation":[{"name":"The Pennsylvania State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4192-0826","authenticated-orcid":false,"given":"Dongsheng","family":"Luo","sequence":"additional","affiliation":[{"name":"Florida International University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0940-6595","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3448-4878","authenticated-orcid":false,"given":"Suhang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,9]]},"reference":[{"key":"e_1_3_1_2_2","article-title":"Graph neural networks for social recommendation","author":"Fan Wenqi","year":"2019","unstructured":"Wenqi Fan, Y. Ma, Qing Li, Yuan He, Y. Zhao, Jiliang Tang, and D. Yin. 2019. Graph neural networks for social recommendation. In Proceedings of the World Wide Web Conference.","journal-title":"Proceedings of the World Wide Web Conference"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411977"},{"key":"e_1_3_1_4_2","first-page":"4517","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI\u201918)","author":"Xu Linli","year":"2018","unstructured":"Linli Xu, Wenjun Ouyang, Xiaoying Ren, Yang Wang, and Liang Jiang. 2018. Enhancing semantic representations of bilingual word embeddings with syntactic dependencies. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI\u201918). 4517\u20134524."},{"key":"e_1_3_1_5_2","article-title":"Molecular geometry prediction using a deep generative graph neural network","volume":"9","author":"Mansimov Elman","year":"2019","unstructured":"Elman Mansimov, O. Mahmood, Seokho Kang, and Kyunghyun Cho. 2019. Molecular geometry prediction using a deep generative graph neural network. Sci. Rep. 9 (2019).","journal-title":"Sci. Rep."},{"key":"e_1_3_1_6_2","first-page":"181","article-title":"Utilizing molecular network information via graph convolutional neural networks to predict metastatic event in breast cancer","volume":"267","author":"Chereda Hryhorii","year":"2019","unstructured":"Hryhorii Chereda, A. Bleckmann, F. Kramer, A. Leha, and T. Bei\u00dfbarth. 2019. Utilizing molecular network information via graph convolutional neural networks to predict metastatic event in breast cancer. Stud. Health Technol. Inform. 267 (2019), 181\u2013186.","journal-title":"Stud. Health Technol. Inform."},{"key":"e_1_3_1_7_2","article-title":"Modeling semantics with gated graph neural networks for knowledge base question answering","volume":"1808","author":"Sorokin Daniil","year":"2018","unstructured":"Daniil Sorokin and Iryna Gurevych. 2018. Modeling semantics with gated graph neural networks for knowledge base question answering. ArXiv abs\/1808.04126 (2018).","journal-title":"ArXiv"},{"issue":"4","key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3501815","article-title":"Federated social recommendation with graph neural network","volume":"13","author":"Liu Zhiwei","year":"2022","unstructured":"Zhiwei Liu, Liangwei Yang, Ziwei Fan, Hao Peng, and Philip S. Yu. 2022. Federated social recommendation with graph neural network. ACM Trans. Intell. Syst. Technol. 13, 4 (2022), 1\u201324.","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"e_1_3_1_9_2","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf Thomas N.","year":"2016","unstructured":"Thomas N. Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).","journal-title":"arXiv preprint arXiv:1609.02907"},{"key":"e_1_3_1_10_2","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107 Petar","year":"2017","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).","journal-title":"arXiv preprint arXiv:1710.10903"},{"key":"e_1_3_1_11_2","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Adv. Neural Inf. Process. Syst. 30 (2017).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_1_12_2","first-page":"543","volume-title":"Proceedings of the 10th International Conference on Knowledge Science, Engineering and Management (KSEM\u201917)","author":"Ren Weijieying","year":"2017","unstructured":"Weijieying Ren, Lei Zhang, Bo Jiang, Zhefeng Wang, Guangming Guo, and Guiquan Liu. 2017. Robust mapping learning for multi-view multi-label classification with missing labels. In Proceedings of the 10th International Conference on Knowledge Science, Engineering and Management (KSEM\u201917). Springer, 543\u2013551."},{"key":"e_1_3_1_13_2","article-title":"How powerful are graph neural networks?","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018).","journal-title":"arXiv preprint arXiv:1810.00826"},{"key":"e_1_3_1_14_2","article-title":"Link prediction based on graph neural networks","volume":"31","author":"Zhang Muhan","year":"2018","unstructured":"Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. Adv. Neural Inf. Process. Syst. 31 (2018).","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3470889","article-title":"Graph sequence neural network with an attention mechanism for traffic speed prediction","volume":"13","author":"Lu Zhilong","year":"2022","unstructured":"Zhilong Lu, Weifeng Lv, Zhipu Xie, Bowen Du, Guixi Xiong, Leilei Sun, and Haiquan Wang. 2022. Graph sequence neural network with an attention mechanism for traffic speed prediction. ACM Trans. Intell. Syst. Technol. 13, 2 (2022), 1\u201324.","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"e_1_3_1_16_2","first-page":"1212","volume-title":"Proceedings of the IEEE International Conference on Data Mining (ICDM\u201918)","author":"Ren Xiaoying","year":"2018","unstructured":"Xiaoying Ren, Linli Xu, Tianxiang Zhao, Chen Zhu, Junliang Guo, and Enhong Chen. 2018. Tracking and forecasting dynamics in crowdfunding: A basis-synthesis approach. In Proceedings of the IEEE International Conference on Data Mining (ICDM\u201918). IEEE, 1212\u20131217."},{"key":"e_1_3_1_17_2","article-title":"Quantitative evaluation of explainable graph neural networks for molecular property prediction","author":"Rao Jiahua","year":"2021","unstructured":"Jiahua Rao, Shuangjia Zheng, and Yuedong Yang. 2021. Quantitative evaluation of explainable graph neural networks for molecular property prediction. arXiv preprint arXiv:2107.04119 (2021).","journal-title":"arXiv preprint arXiv:2107.04119"},{"key":"e_1_3_1_18_2","first-page":"438","volume-title":"Proceedings of the IEEE International Conference on Data Mining (ICDM\u201922)","author":"Ren Weijieying","year":"2022","unstructured":"Weijieying Ren, Lei Wang, Kunpeng Liu, Ruocheng Guo, Lim Ee Peng, and Yanjie Fu. 2022. Mitigating popularity bias in recommendation with unbalanced interactions: A gradient perspective. In Proceedings of the IEEE International Conference on Data Mining (ICDM\u201922). IEEE, 438\u2013447."},{"key":"e_1_3_1_19_2","unstructured":"Xiaoying Ren Jing Jiang Ling Min Serena Khoo and Hai Leong Chieu. 2021. Cross-topic rumor detection using topic-mixtures. Conference of the European Chapter of the Association for Computational Linguistics . https:\/\/api.semanticscholar.org\/CorpusID:233189630"},{"key":"e_1_3_1_20_2","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume":"32","author":"Ying Rex","year":"2019","unstructured":"Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. GNNExplainer: Generating explanations for graph neural networks. Adv. Neural Inf. Process. Syst. 32 (2019), 9240.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_1_21_2","first-page":"19620","article-title":"Parameterized explainer for graph neural network","volume":"33","author":"Luo Dongsheng","year":"2020","unstructured":"Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, and Xiang Zhang. 2020. Parameterized explainer for graph neural network. Adv. Neural Inf. Process. Syst. 33 (2020), 19620\u201319631.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_1_22_2","article-title":"On consistency in graph neural network interpretation","author":"Zhao Tianxiang","year":"2022","unstructured":"Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, and Suhang Wang. 2022. On consistency in graph neural network interpretation. arXiv preprint arXiv:2205.13733 (2022).","journal-title":"arXiv preprint arXiv:2205.13733"},{"key":"e_1_3_1_23_2","article-title":"GraphLIME: Local interpretable model explanations for graph neural networks","author":"Huang Qiang","year":"2020","unstructured":"Qiang Huang, Makoto Yamada, Yuan Tian, Dinesh Singh, Dawei Yin, and Yi Chang. 2020. GraphLIME: Local interpretable model explanations for graph neural networks. arXiv preprint arXiv:2001.06216 (2020).","journal-title":"arXiv preprint arXiv:2001.06216"},{"key":"e_1_3_1_24_2","article-title":"PGMExplainer: Probabilistic graphical model explanations for graph neural networks","author":"Vu Minh N.","year":"2020","unstructured":"Minh N. Vu and My T. Thai. 2020. PGMExplainer: Probabilistic graphical model explanations for graph neural networks. arXiv preprint arXiv:2010.05788 (2020).","journal-title":"arXiv preprint arXiv:2010.05788"},{"key":"e_1_3_1_25_2","first-page":"12241","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Yuan Hao","year":"2021","unstructured":"Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, and Shuiwang Ji. 2021. On explainability of graph neural networks via subgraph explorations. In Proceedings of the International Conference on Machine Learning. PMLR, 12241\u201312252."},{"key":"e_1_3_1_26_2","article-title":"Explainability in graph neural networks: A taxonomic survey","author":"Yuan Hao","year":"2020","unstructured":"Hao Yuan, Haiyang Yu, Shurui Gui, and Shuiwang Ji. 2020. Explainability in graph neural networks: A taxonomic survey. arXiv preprint arXiv:2012.15445 (2020).","journal-title":"arXiv preprint arXiv:2012.15445"},{"key":"e_1_3_1_27_2","article-title":"From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable AI","author":"Nauta Meike","year":"2022","unstructured":"Meike Nauta, Jan Trienes, Shreyasi Pathak, Elisa Nguyen, Michelle Peters, Yasmin Schmitt, J\u00f6rg Schl\u00f6tterer, Maurice van Keulen, and Christin Seifert. 2022. From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable AI. arXiv preprint arXiv:2201.08164 (2022).","journal-title":"arXiv preprint arXiv:2201.08164"},{"key":"e_1_3_1_28_2","article-title":"Towards robust graph neural networks for noisy graphs with sparse labels","author":"Dai Enyan","year":"2022","unstructured":"Enyan Dai, Wei Jin, Hui Liu, and Suhang Wang. 2022. Towards robust graph neural networks for noisy graphs with sparse labels. arXiv preprint arXiv:2201.00232 (2022).","journal-title":"arXiv preprint arXiv:2201.00232"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441720"},{"issue":"1","key":"e_1_3_1_30_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3495161","article-title":"Graph neural networks: Taxonomy, advances, and trends","volume":"13","author":"Zhou Yu","year":"2022","unstructured":"Yu Zhou, Haixia Zheng, Xin Huang, Shufeng Hao, Dengao Li, and Jumin Zhao. 2022. Graph neural networks: Taxonomy, advances, and trends. ACM Trans. Intell. Syst. Technol. 13, 1 (2022), 1\u201354.","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"e_1_3_1_31_2","article-title":"Skill disentanglement for imitation learning from suboptimal demonstrations","author":"Zhao Tianxiang","year":"2023","unstructured":"Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang, Xiang Zhang, Yuncong Chen, Yanchi Liu, Wei Cheng, and Haifeng Chen. 2023. Skill disentanglement for imitation learning from suboptimal demonstrations. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining.","journal-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining"},{"key":"e_1_3_1_32_2","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna Joan","year":"2013","unstructured":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 (2013).","journal-title":"arXiv preprint arXiv:1312.6203"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Ke Liang Jim Tan Dongrui Zeng Yongzhe Huang Xiaolei Huang and Gang Tan. 2023. ABSLearn: a GNN-based framework for aliasing and buffer-size information retrieval. Pattern Analysis and Applications 26 (2023) 1171\u20131189. https:\/\/api.semanticscholar.org\/CorpusID:257129854","DOI":"10.1007\/s10044-023-01142-2"},{"key":"e_1_3_1_34_2","article-title":"Reasoning over different types of knowledge graphs: Static, temporal and multi-modal","author":"Liang Ke","year":"2022","unstructured":"Ke Liang, Lingyuan Meng, Meng Liu, Yue Liu, Wenxuan Tu, Siwei Wang, Sihang Zhou, Xinwang Liu, and Fuchun Sun. 2022. Reasoning over different types of knowledge graphs: Static, temporal and multi-modal. arXiv preprint arXiv:2212.05767 (2022).","journal-title":"arXiv preprint arXiv:2212.05767"},{"key":"e_1_3_1_35_2","first-page":"2224","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","author":"Duvenaud David K.","year":"2015","unstructured":"David K. Duvenaud, Dougal Maclaurin, Jorge Iparraguirre, Rafael Bombarell, Timothy Hirzel, Al\u00e1n Aspuru-Guzik, and Ryan P. Adams. 2015. Convolutional networks on graphs for learning molecular fingerprints. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 2224\u20132232."},{"key":"e_1_3_1_36_2","first-page":"1993","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","author":"Atwood James","year":"2016","unstructured":"James Atwood and Don Towsley. 2016. Diffusion-convolutional neural networks. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 1993\u20132001."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467451"},{"key":"e_1_3_1_38_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. 2017. Neural message passing for quantum Chemistry. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_1_39_2","first-page":"37","volume-title":"Proceedings of the Learning on Graphs Conference","author":"Zhao Tianxiang","year":"2022","unstructured":"Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, and Suhang Wang. 2022. TopoImb: Toward topology-level imbalance in learning from graphs. In Proceedings of the Learning on Graphs Conference. PMLR, 37\u20131."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401137"},{"key":"e_1_3_1_41_2","first-page":"1028","volume-title":"Proceedings of the ACM Web Conference","author":"Zhao Tianxiang","year":"2022","unstructured":"Tianxiang Zhao, Xiang Zhang, and Suhang Wang. 2022. Exploring edge disentanglement for node classification. In Proceedings of the ACM Web Conference. 1028\u20131036."},{"key":"e_1_3_1_42_2","first-page":"arXiv\u20132206","article-title":"Decoupled self-supervised learning for non-homophilous graphs","author":"Xiao Teng","year":"2022","unstructured":"Teng Xiao, Zhengyu Chen, Zhimeng Guo, Zeyang Zhuang, and Suhang Wang. 2022. Decoupled self-supervised learning for non-homophilous graphs. arXiv e-prints (2022), arXiv\u20132206.","journal-title":"arXiv e-prints"},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Shuai Lin Pan Zhou Zi-Yuan Hu Shuojia Wang Ruihui Zhao Yefeng Zheng Liang Lin Eric P. Xing and Xiaodan Liang. 2021. Prototypical graph contrastive learning. IEEE Transactions on Neural Networks and Learning Systems . https:\/\/api.semanticscholar.org\/CorpusID:235457979","DOI":"10.1109\/TNNLS.2022.3191086"},{"key":"e_1_3_1_44_2","article-title":"HP-GMN: Graph memory networks for heterophilous graphs","author":"Xu Junjie","year":"2022","unstructured":"Junjie Xu, Enyan Dai, Xiang Zhang, and Suhang Wang. 2022. HP-GMN: Graph memory networks for heterophilous graphs. arXiv preprint arXiv:2210.08195 (2022).","journal-title":"arXiv preprint arXiv:2210.08195"},{"key":"e_1_3_1_45_2","first-page":"599","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Balcilar Muhammet","year":"2021","unstructured":"Muhammet Balcilar, Pierre H\u00e9roux, Benoit Gauzere, Pascal Vasseur, S\u00e9bastien Adam, and Paul Honeine. 2021. Breaking the limits of message passing graph neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 599\u2013608."},{"key":"e_1_3_1_46_2","article-title":"A survey on the expressive power of graph neural networks","author":"Sato Ryoma","year":"2020","unstructured":"Ryoma Sato. 2020. A survey on the expressive power of graph neural networks. arXiv preprint arXiv:2003.04078 (2020).","journal-title":"arXiv preprint arXiv:2003.04078"},{"key":"e_1_3_1_47_2","article-title":"Revisiting graph neural networks: All we have is low-pass filters","author":"Nt Hoang","year":"2019","unstructured":"Hoang Nt and Takanori Maehara. 2019. Revisiting graph neural networks: All we have is low-pass filters. arXiv preprint arXiv:1905.09550 (2019).","journal-title":"arXiv preprint arXiv:1905.09550"},{"key":"e_1_3_1_48_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201921)","author":"Balcilar Muhammet","year":"2021","unstructured":"Muhammet Balcilar, Renton Guillaume, Pierre H\u00e9roux, Benoit Ga\u00fcz\u00e8re, S\u00e9bastien Adam, and Paul Honeine. 2021. Analyzing the expressive power of graph neural networks in a spectral perspective. In Proceedings of the International Conference on Learning Representations (ICLR\u201921)."},{"key":"e_1_3_1_49_2","doi-asserted-by":"crossref","unstructured":"Sheng-Hsuan Lin and Mohammad Arfan Ikram. 2019. On the relationship of machine learning with causal inference. European Journal of Epidemiology 35 (2019) 183\u2013185. https:\/\/api.semanticscholar.org\/CorpusID:203437853","DOI":"10.1007\/s10654-019-00564-9"},{"key":"e_1_3_1_50_2","article-title":"Explainability techniques for graph convolutional networks","author":"Baldassarre Federico","year":"2019","unstructured":"Federico Baldassarre and Hossein Azizpour. 2019. Explainability techniques for graph convolutional networks. arXiv preprint arXiv:1905.13686 (2019).","journal-title":"arXiv preprint arXiv:1905.13686"},{"key":"e_1_3_1_51_2","article-title":"ProtGNN: Towards self-explaining graph neural networks","author":"Zhang Zaixi","year":"2021","unstructured":"Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, and Cheekong Lee. 2021. ProtGNN: Towards self-explaining graph neural networks. arXiv preprint arXiv:2112.00911 (2021).","journal-title":"arXiv preprint arXiv:2112.00911"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482306"},{"key":"e_1_3_1_53_2","article-title":"A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability","author":"Dai Enyan","year":"2022","unstructured":"Enyan Dai, Tianxiang Zhao, Huaisheng Zhu, Junjie Xu, Zhimeng Guo, Hui Liu, Jiliang Tang, and Suhang Wang. 2022. A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability. arXiv preprint arXiv:2204.08570 (2022).","journal-title":"arXiv preprint arXiv:2204.08570"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01103"},{"key":"e_1_3_1_55_2","article-title":"Reinforcement learning enhanced explainer for graph neural networks","volume":"34","author":"Shan Caihua","year":"2021","unstructured":"Caihua Shan, Yifei Shen, Yao Zhang, Xiang Li, and Dongsheng Li. 2021. Reinforcement learning enhanced explainer for graph neural networks. Adv. Neural Inf. Process. Syst. 34 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_1_56_2","article-title":"Higher-order explanations of graph neural networks via relevant walks","author":"Schnake Thomas","year":"2020","unstructured":"Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Sch\u00fctt, Klaus-Robert M\u00fcller, and Gr\u00e9goire Montavon. 2020. Higher-order explanations of graph neural networks via relevant walks. arXiv preprint arXiv:2006.03589 (2020).","journal-title":"arXiv preprint arXiv:2006.03589"},{"key":"e_1_3_1_57_2","first-page":"6666","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Lin Wanyu","year":"2021","unstructured":"Wanyu Lin, Hao Lan, and Baochun Li. 2021. Generative causal explanations for graph neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 6666\u20136679."},{"key":"e_1_3_1_58_2","article-title":"Discovering invariant rationales for graph neural networks","author":"Wu Ying-Xin","year":"2022","unstructured":"Ying-Xin Wu, Xiang Wang, An Zhang, Xiangnan He, and Tat-Seng Chua. 2022. Discovering invariant rationales for graph neural networks. arXiv preprint arXiv:2201.12872 (2022).","journal-title":"arXiv preprint arXiv:2201.12872"},{"key":"e_1_3_1_59_2","article-title":"Graph information bottleneck for subgraph recognition","author":"Yu Junchi","year":"2020","unstructured":"Junchi Yu, Tingyang Xu, Yu Rong, Yatao Bian, Junzhou Huang, and Ran He. 2020. Graph information bottleneck for subgraph recognition. arXiv preprint arXiv:2010.05563 (2020).","journal-title":"arXiv preprint arXiv:2010.05563"},{"key":"e_1_3_1_60_2","first-page":"1","volume-title":"Proceedings of the IEEE Information Theory Workshop (ITW\u201915)","author":"Tishby Naftali","year":"2015","unstructured":"Naftali Tishby and Noga Zaslavsky. 2015. Deep learning and the information bottleneck principle. In Proceedings of the IEEE Information Theory Workshop (ITW\u201915). IEEE, 1\u20135."},{"key":"e_1_3_1_61_2","doi-asserted-by":"crossref","first-page":"193907","DOI":"10.1109\/ACCESS.2020.3031549","article-title":"Contrastive representation learning: A framework and review","volume":"8","author":"Khac Ph\u00fac H. L\u00ea","year":"2020","unstructured":"Ph\u00fac H. L\u00ea Khac, Graham Healy, and Alan F. Smeaton. 2020. Contrastive representation learning: A framework and review. IEEE Access 8 (2020), 193907\u2013193934.","journal-title":"IEEE Access"},{"key":"e_1_3_1_62_2","article-title":"Supervised contrastive learning","volume":"2004","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. ArXiv abs\/2004.11362 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_1_63_2","first-page":"1597","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In Proceedings of the International Conference on Machine Learning. PMLR, 1597\u20131607."},{"key":"e_1_3_1_64_2","article-title":"Dissecting supervised contrastive learning","volume":"2102","author":"Graf Florian","year":"2021","unstructured":"Florian Graf, Christoph Hofer, Marc Niethammer, and Roland Kwitt. 2021. Dissecting supervised contrastive learning. ArXiv abs\/2102.08817 (2021).","journal-title":"ArXiv"},{"key":"e_1_3_1_65_2","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume":"2005","author":"Wang Tongzhou","year":"2020","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. ArXiv abs\/2005.10242 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_1_66_2","first-page":"1362","volume-title":"Proceedings of the ACM Web Conference","author":"Feng Shengyu","year":"2022","unstructured":"Shengyu Feng, Baoyu Jing, Yada Zhu, and Hanghang Tong. 2022. Adversarial graph contrastive learning with information regularization. In Proceedings of the ACM Web Conference. 1362\u20131371."},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532058"},{"key":"e_1_3_1_68_2","article-title":"An empirical study of graph contrastive learning","author":"Zhu Yanqiao","year":"2021","unstructured":"Yanqiao Zhu, Yichen Xu, Qiang Liu, and Shu Wu. 2021. An empirical study of graph contrastive learning. arXiv preprint arXiv:2109.01116 (2021).","journal-title":"arXiv preprint arXiv:2109.01116"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557317"},{"key":"e_1_3_1_70_2","doi-asserted-by":"crossref","unstructured":"Kenny Ye Liang Yue Liu Sihang Zhou Wenxuan Tu Yi Wen Xihong Yang Xiang Dong and Xinwang Liu. 2022. Knowledge graph contrastive learning based on relation-symmetrical structure. IEEE Transactions on Knowledge and Data Engineering . https:\/\/api.semanticscholar.org\/CorpusID:259145427","DOI":"10.1109\/TKDE.2023.3282989"},{"key":"e_1_3_1_71_2","article-title":"Strategies for pre-training graph neural networks","author":"Hu Weihua","year":"2019","unstructured":"Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay S. Pande, and Jure Leskovec. 2019. Strategies for pre-training graph neural networks. arXiv: Learning (2019).","journal-title":"arXiv: Learning"},{"key":"e_1_3_1_72_2","article-title":"Spatio-temporal deep graph infomax","volume":"1904","author":"Opolka Felix L.","year":"2019","unstructured":"Felix L. Opolka, Aaron Solomon, C\u0103t\u0103lina Cangea, Petar Velickovic, Pietro Lio\u2019, and R. Devon Hjelm. 2019. Spatio-temporal deep graph infomax. ArXiv abs\/1904.06316 (2019).","journal-title":"ArXiv"},{"key":"e_1_3_1_73_2","article-title":"Deep graph infomax","volume":"1809","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, William Fedus, William L. Hamilton, Pietro Lio\u2019, Yoshua Bengio, and R. Devon Hjelm. 2018. Deep graph infomax. ArXiv abs\/1809.10341 (2018).","journal-title":"ArXiv"},{"key":"e_1_3_1_74_2","article-title":"Self-supervised training of graph convolutional networks","volume":"2006","author":"Zhu Qikui","year":"2020","unstructured":"Qikui Zhu, Bo Du, and Pingkun Yan. 2020. Self-supervised training of graph convolutional networks. ArXiv abs\/2006.02380 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_1_75_2","article-title":"Graph contrastive learning with augmentations","volume":"2010","author":"You Yuning","year":"2020","unstructured":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. ArXiv abs\/2010.13902 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_1_76_2","article-title":"Contrastive multi-view representation learning on graphs","volume":"2006","author":"Hassani Kaveh","year":"2020","unstructured":"Kaveh Hassani and Amir Hosein Khas Ahmadi. 2020. Contrastive multi-view representation learning on graphs. ArXiv abs\/2006.05582 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_1_77_2","article-title":"Multi-scale contrastive siamese networks for self-supervised graph representation learning","volume":"2105","author":"Jin Ming","year":"2021","unstructured":"Ming Jin, Yizhen Zheng, Yuan-Fang Li, Chen Gong, Chuan Zhou, and Shirui Pan. 2021. Multi-scale contrastive siamese networks for self-supervised graph representation learning. ArXiv abs\/2105.05682 (2021).","journal-title":"ArXiv"},{"key":"e_1_3_1_78_2","article-title":"Deep graph contrastive representation learning","volume":"2006","author":"Zhu Yanqiao","year":"2020","unstructured":"Yanqiao Zhu, Yichen Xu, Feng Yu, Q. Liu, Shu Wu, and Liang Wang. 2020. Deep graph contrastive representation learning. ArXiv abs\/2006.04131 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_1_79_2","article-title":"ImGCL: Revisiting graph contrastive learning on imbalanced node classification","volume":"2205","author":"Zeng Liang","year":"2022","unstructured":"Liang Zeng, Lanqing Li, Zi-Chao Gao, Peilin Zhao, and Jian Li. 2022. ImGCL: Revisiting graph contrastive learning on imbalanced node classification. ArXiv abs\/2205.11332 (2022).","journal-title":"ArXiv"},{"key":"e_1_3_1_80_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"You Yuning","year":"2021","unstructured":"Yuning You, Tianlong Chen, Yang Shen, and Zhangyang Wang. 2021. Graph contrastive learning automated. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_1_81_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Yin Yihang","year":"2021","unstructured":"Yihang Yin, Qingzhong Wang, Siyu Huang, Haoyi Xiong, and Xiang Zhang. 2021. AutoGCL: Automated graph contrastive learning via learnable view generators. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_1_82_2","first-page":"226","volume-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining","volume":"96","author":"Ester Martin","year":"1996","unstructured":"Martin Ester, Hans-Peter Kriegel, J\u00f6rg Sander, Xiaowei Xu, et\u00a0al. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Vol. 96. 226\u2013231."},{"key":"e_1_3_1_83_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hjelm R. Devon","year":"2018","unstructured":"R. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, and Yoshua Bengio. 2018. Learning deep representations by mutual information estimation and maximization. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_84_2","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1145\/3447548.3467283","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","author":"Faber Lukas","year":"2021","unstructured":"Lukas Faber, Amin K. Moghaddam, and Roger Wattenhofer. 2021. When comparing to ground truth is wrong: On evaluating GNN explanation methods. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 332\u2013341."},{"key":"e_1_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-6889-7"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616542","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:45:32Z","timestamp":1750178732000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,9]]},"references-count":84,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3616542"],"URL":"https:\/\/doi.org\/10.1145\/3616542","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,9]]},"assertion":[{"value":"2023-03-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-24","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}