{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:59:36Z","timestamp":1775667576328,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0106000"],"award-info":[{"award-number":["2020AAA0106000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19A2079, U21B2026"],"award-info":[{"award-number":["U19A2079, U21B2026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539366","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"1696-1705","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":151,"title":["Causal Attention for Interpretable and Generalizable Graph Classification"],"prefix":"10.1145","author":[{"given":"Yongduo","family":"Sui","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Jiancan","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Min","family":"Lin","sequence":"additional","affiliation":[{"name":"Sea AI Lab, Singapore, Singapore"}]},{"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_3_2_2_2_1","volume-title":"Invariant risk minimization. arXiv preprint arXiv:1907.02893","author":"Arjovsky Martin","year":"2019","unstructured":"Martin Arjovsky, L\u00e9on Bottou, Ishaan Gulrajani, and David Lopez-Paz. 2019. Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)."},{"key":"e_1_3_2_2_3_1","volume-title":"Emergence of scaling in random networks. science","author":"Barab\u00e1si Albert-L\u00e1szl\u00f3","year":"1999","unstructured":"Albert-L\u00e1szl\u00f3 Barab\u00e1si and R\u00e9ka Albert. 1999. Emergence of scaling in random networks. science, Vol. 286, 5439 (1999), 509--512."},{"key":"e_1_3_2_2_4_1","unstructured":"Shaked Brody Uri Alon and Eran Yahav. 2022. How Attentive are Graph Attention Networks?. In ICLR."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"e_1_3_2_2_6_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171--4186.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171--4186."},{"key":"e_1_3_2_2_7_1","volume-title":"et almbox","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et almbox. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_2_8_1","volume-title":"Benchmarking graph neural networks. arXiv preprint arXiv:2003.00982","author":"Dwivedi Vijay Prakash","year":"2020","unstructured":"Vijay Prakash Dwivedi, Chaitanya K Joshi, Thomas Laurent, Yoshua Bengio, and Xavier Bresson. 2020. Benchmarking graph neural networks. arXiv preprint arXiv:2003.00982 (2020)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Fuli Feng Weiran Huang Xiangnan He Xin Xin Qifan Wang and Tat-Seng Chua. 2021. Should graph convolution trust neighbors? a simple causal inference method. In SIGIR. 1208--1218.","DOI":"10.1145\/3404835.3462971"},{"key":"e_1_3_2_2_10_1","unstructured":"Hongyang Gao and Shuiwang Ji. 2019. Graph u-nets. In ICML. 2083--2092."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_3_2_2_12_1","volume-title":"ImageNet-trained CNNs are biased towards texture","author":"Geirhos Robert","unstructured":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, and Wieland Brendel. 2019. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In ICLR."},{"key":"e_1_3_2_2_13_1","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. In ICLR."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Jie Hu Li Shen and Gang Sun. 2018. Squeeze-and-excitation networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_2_15_1","unstructured":"Xinting Hu Kaihua Tang Chunyan Miao Xian-Sheng Hua and Hanwang Zhang. 2021. Distilling Causal Effect of Data in Class-Incremental Learning. In CVPR."},{"key":"e_1_3_2_2_16_1","unstructured":"Dongkwan Kim and Alice Oh. 2020. How to find your friendly neighborhood: Graph attention design with self-supervision. In ICLR."},{"key":"e_1_3_2_2_17_1","volume-title":"Kipf and Max Welling","author":"Thomas","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR."},{"key":"e_1_3_2_2_18_1","volume-title":"Amer","author":"Knyazev Boris","year":"2019","unstructured":"Boris Knyazev, Graham W. Taylor, and Mohamed R. Amer. 2019. Understanding Attention and Generalization in Graph Neural Networks. In NeurIPS. 4204--4214."},{"key":"e_1_3_2_2_19_1","unstructured":"Junhyun Lee Inyeop Lee and Jaewoo Kang. 2019 a. Self-attention graph pooling. In ICML. 3734--3743."},{"key":"e_1_3_2_2_20_1","unstructured":"John Boaz Lee Ryan Rossi and Xiangnan Kong. 2018. Graph classification using structural attention. In SIGKDD. 1666--1674."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"John Boaz Lee Ryan A Rossi Xiangnan Kong Sungchul Kim Eunyee Koh and Anup Rao. 2019 b. Graph convolutional networks with motif-based attention. In CIKM. 499--508.","DOI":"10.1145\/3357384.3357880"},{"key":"e_1_3_2_2_22_1","volume-title":"Zemel","author":"Li Yujia","year":"2016","unstructured":"Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard S. Zemel. 2016. Gated Graph Sequence Neural Networks. In ICLR."},{"key":"e_1_3_2_2_23_1","unstructured":"Wanyu Lin Hao Lan and Baochun Li. 2021. Generative causal explanations for graph neural networks. In ICML. 6666--6679."},{"key":"e_1_3_2_2_24_1","volume-title":"Tudataset: A collection of benchmark datasets for learning with graphs. ICMLW.","author":"Morris Christopher","year":"2020","unstructured":"Christopher Morris, Nils M Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and Marion Neumann. 2020. Tudataset: A collection of benchmark datasets for learning with graphs. ICMLW."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Yulei Niu Kaihua Tang Hanwang Zhang Zhiwu Lu Xian-Sheng Hua and Ji-Rong Wen. 2021. Counterfactual vqa: A cause-effect look at language bias. In CVPR. 12700--12710.","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"e_1_3_2_2_26_1","volume-title":"Interpretation and identification of causal mediation. Psychological methods","author":"Pearl Judea","year":"2014","unstructured":"Judea Pearl. 2014. Interpretation and identification of causal mediation. Psychological methods, Vol. 19, 4 (2014), 459."},{"key":"e_1_3_2_2_27_1","volume-title":"mbox","author":"Judea Pearl","year":"2000","unstructured":"Judea Pearl et almbox. 2000. Models, reasoning and inference. Cambridge, UK: Cambridge University Press, Vol. 19 (2000)."},{"key":"e_1_3_2_2_28_1","volume-title":"Pradeep Kumar Ravikumar, and Andrej Risteski","author":"Rosenfeld Elan","year":"2020","unstructured":"Elan Rosenfeld, Pradeep Kumar Ravikumar, and Andrej Risteski. 2020. The Risks of Invariant Risk Minimization. In ICLR."},{"key":"e_1_3_2_2_29_1","volume-title":"Tatsunori B Hashimoto, and Percy Liang.","author":"Sagawa Shiori","year":"2020","unstructured":"Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang. 2020. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. In ICLR."},{"key":"e_1_3_2_2_30_1","article-title":"Weisfeiler-Lehman graph kernels","volume":"12","author":"Shervashidze Nino","year":"2011","unstructured":"Nino Shervashidze, Pascal Schweitzer, Erik Jan Van Leeuwen, Kurt Mehlhorn, and Karsten M Borgwardt. 2011. Weisfeiler-Lehman graph kernels. Journal of Machine Learning Research, Vol. 12, 9 (2011).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_31_1","volume-title":"Borgwardt","author":"Shervashidze Nino","year":"2009","unstructured":"Nino Shervashidze, S. V. N. Vishwanathan, Tobias Petri, Kurt Mehlhorn, and Karsten M. Borgwardt. 2009. Efficient graphlet kernels for large graph comparison. In AISTATS."},{"key":"e_1_3_2_2_32_1","unstructured":"Kaihua Tang Jianqiang Huang and Hanwang Zhang. 2020. Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect. In NeurIPS."},{"key":"e_1_3_2_2_33_1","volume-title":"Attention-based graph neural network for semi-supervised learning. arXiv preprint arXiv:1803.03735","author":"Thekumparampil Kiran K","year":"2018","unstructured":"Kiran K Thekumparampil, Chong Wang, Sewoong Oh, and Li-Jia Li. 2018. Attention-based graph neural network for semi-supervised learning. arXiv preprint arXiv:1803.03735 (2018)."},{"key":"e_1_3_2_2_34_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS. 5998--6008."},{"key":"e_1_3_2_2_35_1","unstructured":"Petar Velivc kovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph Attention Networks. In ICLR."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Tan Wang Chang Zhou Qianru Sun and Hanwang Zhang. 2021 b. Causal Attention for Unbiased Visual Recognition. In CVPR. 3091--3100.","DOI":"10.1109\/ICCV48922.2021.00308"},{"key":"e_1_3_2_2_37_1","volume-title":"Reinforced Causal Explainer for Graph Neural Networks. TPAMI","author":"Wang Xiang","year":"2022","unstructured":"Xiang Wang, Yingxin Wu, An Zhang, Fuli Feng, Xiangnan He, and Tat-Seng Chua. 2022. Reinforced Causal Explainer for Graph Neural Networks. TPAMI (2022)."},{"key":"e_1_3_2_2_38_1","unstructured":"Xiang Wang Yingxin Wu An Zhang Xiangnan He and Tat seng Chua. 2021 a. Towards Multi-Grained Explainability for Graph Neural Networks. In NeurIPS."},{"key":"e_1_3_2_2_39_1","unstructured":"Yingxin Wu Xiang Wang An Zhang Xiangnan He and Tat-Seng Chua. 2022. Discovering Invariant Rationales for Graph Neural Networks. In ICLR."},{"key":"e_1_3_2_2_40_1","unstructured":"Kelvin Xu Jimmy Ba Ryan Kiros Kyunghyun Cho Aaron C. Courville Ruslan Salakhutdinov Richard S. Zemel and Yoshua Bengio. 2015. Show Attend and Tell: Neural Image Caption Generation with Visual Attention. In ICML."},{"key":"e_1_3_2_2_41_1","unstructured":"Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In ICLR."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Pinar Yanardag and SVN Vishwanathan. 2015. Deep graph kernels. In SIGKDD.","DOI":"10.1145\/2783258.2783417"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Xu Yang Hanwang Zhang Guojun Qi and Jianfei Cai. 2021. Causal attention for vision-language tasks. In CVPR. 9847--9857.","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"e_1_3_2_2_44_1","unstructured":"Zhitao Ying Dylan Bourgeois Jiaxuan You Marinka Zitnik and Jure Leskovec. 2019. GNNExplainer: Generating Explanations for Graph Neural Networks. In NeurIPS. 9240--9251."},{"key":"e_1_3_2_2_45_1","unstructured":"Zhitao Ying Jiaxuan You Christopher Morris Xiang Ren William L. Hamilton and Jure Leskovec. 2018. Hierarchical Graph Representation Learning with Differentiable Pooling. In NeurIPS. 4805--4815."},{"key":"e_1_3_2_2_46_1","volume-title":"XGNN: Towards Model-Level Explanations of Graph Neural Networks. In SIGKDD. 430--438.","author":"Yuan Hao","year":"2020","unstructured":"Hao Yuan, Jiliang Tang, Xia Hu, and Shuiwang Ji. 2020. XGNN: Towards Model-Level Explanations of Graph Neural Networks. In SIGKDD. 430--438."},{"key":"e_1_3_2_2_47_1","volume-title":"Petar Velivc kovi\u0107, and Kristian Kersting.","author":"Matej Zevc","year":"2021","unstructured":"Matej Zevc evi\u0107, Devendra Singh Dhami, Petar Velivc kovi\u0107, and Kristian Kersting. 2021. Relating Graph Neural Networks to Structural Causal Models. arXiv preprint arXiv:2109.04173 (2021)."},{"key":"e_1_3_2_2_48_1","unstructured":"Dong Zhang Hanwang Zhang Jinhui Tang Xian-Sheng Hua and Qianru Sun. 2020. Causal Intervention for Weakly-Supervised Semantic Segmentation. In NeurIPS."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Muhan Zhang Zhicheng Cui Marion Neumann and Yixin Chen. 2018. An end-to-end deep learning architecture for graph classification. In AAAI.","DOI":"10.1609\/aaai.v32i1.11782"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539366","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:47Z","timestamp":1750186967000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539366"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":49,"alternative-id":["10.1145\/3534678.3539366","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539366","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}