{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T02:16:15Z","timestamp":1786241775061,"version":"build-2736575974"},"reference-count":92,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T00:00:00Z","timestamp":1711411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021ZD0111802"],"award-info":[{"award-number":["2021ZD0111802"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["92270114"],"award-info":[{"award-number":["92270114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2024,6,30]]},"abstract":"<jats:p>\n            In graph classification, attention- and pooling-based graph neural networks (GNNs) predominate to extract salient features from the input graph and support the prediction. They mostly follow the paradigm of \u201clearning to attend,\u201d which maximizes the mutual information between the attended graph and the ground-truth label. However, this paradigm causes GNN classifiers to indiscriminately absorb all statistical correlations between input features and labels in the training data without distinguishing the causal and noncausal effects of features. Rather than emphasizing causal features, the attended graphs tend to rely on noncausal features as shortcuts to predictions. These shortcut features may easily change outside the training distribution, thereby leading to poor generalization for GNN classifiers. In this article, we take a causal view on GNN modeling. Under our causal assumption, the shortcut feature serves as a confounder between the causal feature and prediction. It misleads the classifier into learning spurious correlations that facilitate prediction in in-distribution (ID) test evaluation while causing significant performance drop in out-of-distribution (OOD) test data. To address this issue, we employ the backdoor adjustment from causal theory\u2014combining each causal feature with various shortcut features, to identify causal patterns and mitigate the confounding effect. Specifically, we employ attention modules to estimate the causal and shortcut features of the input graph. Then, a memory bank collects the estimated shortcut features, enhancing the diversity of shortcut features for combination. Simultaneously, we apply the prototype strategy to improve the consistency of intra-class causal features. We term our method as CAL+, which can promote stable relationships between causal estimation and prediction, regardless of distribution changes. Extensive experiments on synthetic and real-world OOD benchmarks demonstrate our method\u2019s effectiveness in improving OOD generalization. Our codes are released at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/shuyao-wang\/CAL-plus\">https:\/\/github.com\/shuyao-wang\/CAL-plus<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3644392","type":"journal-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T07:04:17Z","timestamp":1707203057000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Enhancing Out-of-distribution Generalization on Graphs via Causal Attention Learning"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4492-147X","authenticated-orcid":false,"given":"Yongduo","family":"Sui","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1348-8412","authenticated-orcid":false,"given":"Wenyu","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0439-4249","authenticated-orcid":false,"given":"Shuyao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6148-6329","authenticated-orcid":false,"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6941-5218","authenticated-orcid":false,"given":"Jiancan","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-7992","authenticated-orcid":false,"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,3,26]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_3_1_3_2","article-title":"Invariant risk minimization","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).","journal-title":"arXiv preprint arXiv:1907.02893"},{"key":"e_1_3_1_4_2","first-page":"837","volume-title":"ICML","author":"Bevilacqua Beatrice","year":"2021","unstructured":"Beatrice Bevilacqua, Yangze Zhou, and Bruno Ribeiro. 2021. Size-invariant graph representations for graph classification extrapolations. In ICML. PMLR, 837\u2013851."},{"key":"e_1_3_1_5_2","volume-title":"ICLR","author":"Brody Shaked","year":"2022","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2022. How attentive are graph attention networks? In ICLR."},{"key":"e_1_3_1_6_2","volume-title":"NeurIPS","author":"Buffelli Davide","year":"2022","unstructured":"Davide Buffelli, Pietro Lio, and Fabio Vandin. 2022. SizeShiftReg: A regularization method for improving size-generalization in graph neural networks. In NeurIPS."},{"key":"e_1_3_1_7_2","volume-title":"NeurIPS","author":"Chen Yongqiang","year":"2023","unstructured":"Yongqiang Chen, Yatao Bian, Kaiwen Zhou, Binghui Xie, Bo Han, and James Cheng. 2023. Does invariant graph learning via environment augmentation learn invariance? In NeurIPS. Retrieved from https:\/\/openreview.net\/forum?id=EqpR9Vtt13"},{"key":"e_1_3_1_8_2","volume-title":"ICML DG Workshop","author":"Chen Yongqiang","year":"2023","unstructured":"Yongqiang Chen, Yatao Bian, Kaiwen Zhou, Binghui Xie, Bo Han, and James Cheng. 2023. Rethinking invariant graph representation learning without environment partitions In ICML DG Workshop."},{"key":"e_1_3_1_9_2","first-page":"22131","article-title":"Learning causally invariant representations for out-of-distribution generalization on graphs","volume":"35","author":"Chen Yongqiang","year":"2022","unstructured":"Yongqiang Chen, Yonggang Zhang, Yatao Bian, Han Yang, M. A. Kaili, Binghui Xie, Tongliang Liu, Bo Han, and James Cheng. 2022. Learning causally invariant representations for out-of-distribution generalization on graphs. Neural Inf. Process. 35 (2022), 22131\u201322148.","journal-title":"Neural Inf. Process."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"e_1_3_1_11_2","first-page":"4171","volume-title":"NAACL","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\u20134186."},{"key":"e_1_3_1_12_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR."},{"key":"e_1_3_1_13_2","article-title":"Benchmarking graph neural networks","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).","journal-title":"arXiv preprint arXiv:2003.00982"},{"key":"e_1_3_1_14_2","volume-title":"NeurIPS","author":"Fan Shaohua","unstructured":"Shaohua Fan, Xiao Wang, Yanhu Mo, Chuan Shi, and Jian Tang. 2022. Debiasing graph neural networks via learning disentangled causal substructure. In NeurIPS."},{"key":"e_1_3_1_15_2","article-title":"Generalizing graph neural networks on out-of-distribution graphs","author":"Fan Shaohua","year":"2021","unstructured":"Shaohua Fan, Xiao Wang, Chuan Shi, Peng Cui, and Bai Wang. 2021. Generalizing graph neural networks on out-of-distribution graphs. arXiv preprint arXiv:2111.10657 (2021).","journal-title":"arXiv preprint arXiv:2111.10657"},{"key":"e_1_3_1_16_2","volume-title":"NeurIPS","author":"Fang Junfeng","year":"2023","unstructured":"Junfeng Fang, Wei Liu, Yuan Gao, Zemin Liu, An Zhang, Xiang Wang, and Xiangnan He. 2023. Evaluating post-hoc explanations for graph neural networks via robustness analysis. In NeurIPS."},{"key":"e_1_3_1_17_2","first-page":"616","volume-title":"WSDM","author":"Fang Junfeng","year":"2023","unstructured":"Junfeng Fang, Xiang Wang, An Zhang, Zemin Liu, Xiangnan He, and Tat-Seng Chua. 2023. Cooperative explanations of graph neural networks. In WSDM. ACM, 616\u2013624."},{"key":"e_1_3_1_18_2","first-page":"1208","volume-title":"SIGIR","author":"Feng Fuli","year":"2021","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\u20131218."},{"key":"e_1_3_1_19_2","first-page":"2083","volume-title":"ICML","author":"Gao Hongyang","year":"2019","unstructured":"Hongyang Gao and Shuiwang Ji. 2019. Graph U-Nets. In ICML. 2083\u20132092."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-1531-9"},{"key":"e_1_3_1_21_2","first-page":"1528","volume-title":"WWW","author":"Gao Yuan","year":"2023","unstructured":"Yuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu, Huamin Feng, and Yongdong Zhang. 2023. Addressing heterophily in graph anomaly detection: A perspective of graph spectrum. In WWW. ACM, 1528\u20131538."},{"key":"e_1_3_1_22_2","first-page":"357","volume-title":"WSDM","author":"Gao Yuan","year":"2023","unstructured":"Yuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu, Huamin Feng, and Yongdong Zhang. 2023. Alleviating structural distribution shift in graph anomaly detection. In WSDM. ACM, 357\u2013365."},{"key":"e_1_3_1_23_2","unstructured":"Shurui Gui Xiner Li Limei Wang and Shuiwang Ji. 2022. Good: A graph out-of-distribution benchmark. In NeurIPS."},{"key":"e_1_3_1_24_2","first-page":"8230","volume-title":"ICML","author":"Han Xiaotian","year":"2022","unstructured":"Xiaotian Han, Zhimeng Jiang, Ninghao Liu, and Xia Hu. 2022. G-mixup: Graph data augmentation for graph classification. In ICML. PMLR, 8230\u20138248."},{"key":"e_1_3_1_25_2","first-page":"9729","volume-title":"CVPR","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In CVPR. 9729\u20139738."},{"key":"e_1_3_1_26_2","volume-title":"ICLR","author":"Hendrycks Dan","year":"2017","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_1_27_2","unstructured":"Miguel A. Hernan and James M. Robins. 2010. Causal Inference: What If. CRC Press."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1986.10478354"},{"key":"e_1_3_1_29_2","volume-title":"CVPR","author":"Hu Jie","year":"2018","unstructured":"Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-excitation networks. In CVPR."},{"key":"e_1_3_1_30_2","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. Neural Inf. Process. 33 (2020), 22118\u201322133.","journal-title":"Neural Inf. Process."},{"key":"e_1_3_1_31_2","volume-title":"CVPR","author":"Hu Xinting","year":"2021","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_1_32_2","volume-title":"ICLR","author":"Jin Wei","year":"2023","unstructured":"Wei Jin, Tong Zhao, Jiayuan Ding, Yozen Liu, Jiliang Tang, and Neil Shah. 2023. Empowering graph representation learning with test-time graph transformation. In ICLR."},{"key":"e_1_3_1_33_2","volume-title":"ICLR","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 ICLR."},{"key":"e_1_3_1_34_2","volume-title":"ICLR","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR."},{"key":"e_1_3_1_35_2","first-page":"4204","volume-title":"NeurIPS","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\u20134214."},{"key":"e_1_3_1_36_2","first-page":"60","volume-title":"CVPR","author":"Kong Kezhi","year":"2022","unstructured":"Kezhi Kong, Guohao Li, Mucong Ding, Zuxuan Wu, Chen Zhu, Bernard Ghanem, Gavin Taylor, and Tom Goldstein. 2022. Robust optimization as data augmentation for large-scale graphs. In CVPR. 60\u201369."},{"key":"e_1_3_1_37_2","first-page":"5815","volume-title":"ICML","author":"Krueger David","year":"2021","unstructured":"David Krueger, Ethan Caballero, Joern-Henrik Jacobsen, Amy Zhang, Jonathan Binas, Dinghuai Zhang, Remi Le Priol, and Aaron Courville. 2021. Out-of-distribution generalization via risk extrapolation (REX). In ICML. PMLR, 5815\u20135826."},{"key":"e_1_3_1_38_2","first-page":"3734","volume-title":"ICML","author":"Lee Junhyun","year":"2019","unstructured":"Junhyun Lee, Inyeop Lee, and Jaewoo Kang. 2019. Self-attention graph pooling. In ICML. 3734\u20133743."},{"key":"e_1_3_1_39_2","first-page":"1666","volume-title":"KDD","author":"Lee John Boaz","year":"2018","unstructured":"John Boaz Lee, Ryan Rossi, and Xiangnan Kong. 2018. Graph classification using structural attention. In KDD. 1666\u20131674."},{"key":"e_1_3_1_40_2","first-page":"499","volume-title":"CIKM","author":"Lee John Boaz","year":"2019","unstructured":"John Boaz Lee, Ryan A. Rossi, Xiangnan Kong, Sungchul Kim, Eunyee Koh, and Anup Rao. 2019. Graph convolutional networks with motif-based attention. In CIKM. 499\u2013508."},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","unstructured":"Haoyang Li Xin Wang Ziwei Zhang and Wenwu Zhu. 2023. OOD-GNN: Out-of-distribution generalized graph neural network. IEEE Transactions on Knowledge and Data Engineering 35 7 (2023) 7328\u20137340. DOI:10.1109\/TKDE.2022.3193725","DOI":"10.1109\/TKDE.2022.3193725"},{"key":"e_1_3_1_42_2","article-title":"Out-of-distribution generalization on graphs: A survey","author":"Li Haoyang","year":"2022","unstructured":"Haoyang Li, Xin Wang, Ziwei Zhang, and Wenwu Zhu. 2022. Out-of-distribution generalization on graphs: A survey. arXiv preprint arXiv:2202.07987 (2022).","journal-title":"arXiv preprint arXiv:2202.07987"},{"key":"e_1_3_1_43_2","volume-title":"NeurIPS","author":"Li Haoyang","year":"2022","unstructured":"Haoyang Li, Ziwei Zhang, Xin Wang, and Wenwu Zhu. 2022. Learning invariant graph representations for out-of-distribution generalization. In NeurIPS."},{"issue":"1","key":"e_1_3_1_44_2","first-page":"1","article-title":"Invariant node representation learning under distribution shifts with multiple latent environments","volume":"42","author":"Li Haoyang","year":"2023","unstructured":"Haoyang Li, Ziwei Zhang, Xin Wang, and Wenwu Zhu. 2023. Invariant node representation learning under distribution shifts with multiple latent environments. ACM Trans. Inf. Syst. 42, 1 (2023), 1\u201330.","journal-title":"ACM Trans. Inf. Syst."},{"key":"e_1_3_1_45_2","volume-title":"ICLR","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_1_46_2","first-page":"6666","volume-title":"ICML","author":"Lin Wanyu","year":"2021","unstructured":"Wanyu Lin, Hao Lan, and Baochun Li. 2021. Generative causal explanations for graph neural networks. In ICML. PMLR, 6666\u20136679."},{"key":"e_1_3_1_47_2","first-page":"24529","article-title":"ZIN: When and how to learn invariance without environment partition?","volume":"35","author":"Lin Yong","year":"2022","unstructured":"Yong Lin, Shengyu Zhu, Lu Tan, and Peng Cui. 2022. ZIN: When and how to learn invariance without environment partition? Neural Inf. Process 35 (2022), 24529\u201324542.","journal-title":"Neural Inf. Process"},{"key":"e_1_3_1_48_2","first-page":"1069","volume-title":"KDD","author":"Liu Gang","year":"2022","unstructured":"Gang Liu, Tong Zhao, Jiaxin Xu, Tengfei Luo, and Meng Jiang. 2022. Graph rationalization with environment-based augmentations. In KDD. 1069\u20131078."},{"key":"e_1_3_1_49_2","first-page":"7313","volume-title":"ICML","author":"Mahajan Divyat","year":"2021","unstructured":"Divyat Mahajan, Shruti Tople, and Amit Sharma. 2021. Domain generalization using causal matching. In ICML. PMLR, 7313\u20137324."},{"key":"e_1_3_1_50_2","first-page":"15524","volume-title":"ICML","author":"Miao Siqi","year":"2022","unstructured":"Siqi Miao, Mia Liu, and Pan Li. 2022. Interpretable and generalizable graph learning via stochastic attention mechanism. In ICML. PMLR, 15524\u201315543."},{"key":"e_1_3_1_51_2","article-title":"Tudataset: A collection of benchmark datasets for learning with graphs","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. In ICMLW.","journal-title":"ICMLW"},{"key":"e_1_3_1_52_2","first-page":"12700","volume-title":"CVPR","author":"Niu Yulei","year":"2021","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\u201312710."},{"key":"e_1_3_1_53_2","unstructured":"Judea Pearl. 2010. Causal inference. Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008 (PMLR) Proceedings of Machine Learning Research Vol. 6 39\u201358."},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1037\/a0036434"},{"key":"e_1_3_1_55_2","article-title":"Models, reasoning and inference","volume":"19","author":"Pearl Judea","year":"2000","unstructured":"Judea Pearl. 2000. Models, reasoning and inference. Cambridge, UK: Cambridge University Press 19 (2000).","journal-title":"Cambridge, UK: Cambridge University Press"},{"key":"e_1_3_1_56_2","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"Pearl Judea","year":"2018","unstructured":"Judea Pearl and Dana Mackenzie. 2018. The Book of Why: The New Science of Cause and Effect. Basic Books."},{"key":"e_1_3_1_57_2","unstructured":"Qi Qi Jiameng Lyu Kung sik Chan Er Wei Bai and Tianbao Yang. 2022. Stochastic constrained DRO with a complexity independent of sample size. arXiv preprint arXiv:2210.05740 (2022)."},{"key":"e_1_3_1_58_2","article-title":"Attentional biased stochastic gradient for imbalanced classification","author":"Qi Qi","year":"2020","unstructured":"Qi Qi, Yi Xu, Rong Jin, Wotao Yin, and Tianbao Yang. 2020. Attentional biased stochastic gradient for imbalanced classification. arXiv preprint arXiv:2012.06951 (2020).","journal-title":"arXiv preprint arXiv:2012.06951"},{"key":"e_1_3_1_59_2","article-title":"DropEdge: Towards deep graph convolutional networks on node classification","author":"Rong Yu","year":"2019","unstructured":"Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. 2019. DropEdge: Towards deep graph convolutional networks on node classification. arXiv preprint arXiv:1907.10903 (2019).","journal-title":"arXiv preprint arXiv:1907.10903"},{"key":"e_1_3_1_60_2","volume-title":"ICLR","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_1_61_2","volume-title":"ICLR","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_1_62_2","first-page":"1","volume-title":"IJCNN","author":"Sui Yongduo","year":"2022","unstructured":"Yongduo Sui, Tianlong Chen, Pengfei Xia, Shuyao Wang, and Bin Li. 2022. Towards robust detection and segmentation using vertical and horizontal adversarial training. In IJCNN. IEEE, 1\u20138."},{"key":"e_1_3_1_63_2","article-title":"Inductive lottery ticket learning for graph neural networks","author":"Sui Yongduo","year":"2023","unstructured":"Yongduo Sui, Xiang Wang, Tianlong Chen, Meng Wang, Xiangnan He, and Tat-Seng Chua. 2023. Inductive lottery ticket learning for graph neural networks. J. Comput. Sci. Technol. (2023).","journal-title":"J. Comput. Sci. Technol."},{"key":"e_1_3_1_64_2","first-page":"1696","volume-title":"KDD","author":"Sui Yongduo","year":"2022","unstructured":"Yongduo Sui, Xiang Wang, Jiancan Wu, Min Lin, Xiangnan He, and Tat-Seng Chua. 2022. Causal attention for interpretable and generalizable graph classification. In KDD. 1696\u20131705."},{"key":"e_1_3_1_65_2","volume-title":"NeurIPS","author":"Sui Yongduo","year":"2023","unstructured":"Yongduo Sui, Qitian Wu, Jiancan Wu, Qing Cui, Longfei Li, Jun Zhou, Xiang Wang, and Xiangnan He. 2023. Unleashing the power of graph data augmentation on covariate distribution shift. In NeurIPS."},{"key":"e_1_3_1_66_2","volume-title":"NeurIPS","author":"Tang Kaihua","year":"2020","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_1_67_2","article-title":"Attention-based graph neural network for semi-supervised learning","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).","journal-title":"arXiv preprint arXiv:1803.03735"},{"key":"e_1_3_1_68_2","first-page":"5998","volume-title":"NeurIPS","author":"Vaswani Ashish","year":"2017","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\u20136008."},{"key":"e_1_3_1_69_2","volume-title":"ICLR","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In ICLR."},{"key":"e_1_3_1_70_2","first-page":"3091","volume-title":"CVPR","author":"Wang Tan","year":"2021","unstructured":"Tan Wang, Chang Zhou, Qianru Sun, and Hanwang Zhang. 2021. Causal attention for unbiased visual recognition. In CVPR. 3091\u20133100."},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","unstructured":"Xiang Wang Yingxin Wu An Zhang Fuli Feng Xiangnan He and Tat-Seng Chua. 2023. Reinforced causal explainer for graph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 2 (2023) 2297\u20132309. DOI:10.1109\/TPAMI.2022.3170302","DOI":"10.1109\/TPAMI.2022.3170302"},{"key":"e_1_3_1_72_2","volume-title":"NeurIPS","author":"Wang Xiang","year":"2021","unstructured":"Xiang Wang, Yingxin Wu, An Zhang, Xiangnan He, and Tat seng Chua. 2021. Towards multi-grained explainability for graph neural networks. In NeurIPS."},{"key":"e_1_3_1_73_2","article-title":"Customized graph neural networks","author":"Wang Yiqi","year":"2020","unstructured":"Yiqi Wang, Yao Ma, Wei Jin, Chaozhuo Li, Charu Aggarwal, and Jiliang Tang. 2020. Customized graph neural networks. arXiv preprint arXiv:2005.12386 (2020).","journal-title":"arXiv preprint arXiv:2005.12386"},{"key":"e_1_3_1_74_2","first-page":"3663","volume-title":"WWW","author":"Wang Yiwei","year":"2021","unstructured":"Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, and Bryan Hooi. 2021. Mixup for node and graph classification. In WWW. 3663\u20133674."},{"key":"e_1_3_1_75_2","volume-title":"ICLR","author":"Wu Qitian","year":"2022","unstructured":"Qitian Wu, Hengrui Zhang, Junchi Yan, and David Wipf. 2022. Handling distribution shifts on graphs: An invariance perspective. In ICLR."},{"key":"e_1_3_1_76_2","volume-title":"ICLR","author":"Wu Yingxin","year":"2022","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_1_77_2","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"e_1_3_1_78_2","first-page":"3733","volume-title":"CVPR","author":"Wu Zhirong","year":"2018","unstructured":"Zhirong Wu, Yuanjun Xiong, Stella X. Yu, and Dahua Lin. 2018. Unsupervised feature learning via non-parametric instance discrimination. In CVPR. 3733\u20133742."},{"key":"e_1_3_1_79_2","volume-title":"ICML","author":"Xu Kelvin","year":"2015","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_1_80_2","volume-title":"ICLR","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How powerful are graph neural networks? In ICLR."},{"key":"e_1_3_1_81_2","volume-title":"NeurIPS","author":"Yang Nianzu","year":"2022","unstructured":"Nianzu Yang, Kaipeng Zeng, Qitian Wu, Xiaosong Jia, and Junchi Yan. 2022. Learning substructure invariance for out-of-distribution molecular representations. In NeurIPS."},{"key":"e_1_3_1_82_2","first-page":"9847","volume-title":"CVPR","author":"Yang Xu","year":"2021","unstructured":"Xu Yang, Hanwang Zhang, Guojun Qi, and Jianfei Cai. 2021. Causal attention for vision-language tasks. In CVPR. 9847\u20139857."},{"key":"e_1_3_1_83_2","first-page":"11975","volume-title":"ICML","author":"Yehudai Gilad","year":"2021","unstructured":"Gilad Yehudai, Ethan Fetaya, Eli Meirom, Gal Chechik, and Haggai Maron. 2021. From local structures to size generalization in graph neural networks. In ICML. PMLR, 11975\u201311986."},{"key":"e_1_3_1_84_2","first-page":"9240","volume-title":"NeurIPS","author":"Ying Zhitao","year":"2019","unstructured":"Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. GNNExplainer: Generating explanations for graph neural networks. In NeurIPS. 9240\u20139251."},{"key":"e_1_3_1_85_2","first-page":"4805","volume-title":"NeurIPS","author":"Ying Zhitao","year":"2018","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\u20134815."},{"key":"e_1_3_1_86_2","volume-title":"CVPR","author":"Yu Junchi","year":"2023","unstructured":"Junchi Yu, Jian Liang, and Ran He. 2023. Mind the label shift of augmentation-based graph OOD generalization. In CVPR."},{"key":"e_1_3_1_87_2","first-page":"430","volume-title":"KDD","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 KDD. 430\u2013438."},{"key":"e_1_3_1_88_2","article-title":"Relating graph neural networks to structural causal models","author":"Ze\u010devi\u0107 Matej","year":"2021","unstructured":"Matej Ze\u010devi\u0107, Devendra Singh Dhami, Petar Veli\u010dkovi\u0107, and Kristian Kersting. 2021. Relating graph neural networks to structural causal models. arXiv preprint arXiv:2109.04173 (2021).","journal-title":"arXiv preprint arXiv:2109.04173"},{"key":"e_1_3_1_89_2","volume-title":"NeurIPS","author":"Zhang Dong","year":"2020","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_1_90_2","volume-title":"AAAI","author":"Zhang Muhan","year":"2018","unstructured":"Muhan Zhang, Zhicheng Cui, Marion Neumann, and Yixin Chen. 2018. An end-to-end deep learning architecture for graph classification. In AAAI."},{"key":"e_1_3_1_91_2","first-page":"26484","volume-title":"ICML","author":"Zhang Michael","year":"2022","unstructured":"Michael Zhang, Nimit S. Sohoni, Hongyang R. Zhang, Chelsea Finn, and Christopher Re. 2022. Correct-N-contrast: A contrastive approach for improving robustness to spurious correlations. In ICML. PMLR, 26484\u201326516."},{"key":"e_1_3_1_92_2","first-page":"5372","volume-title":"CVPR","author":"Zhang Xingxuan","year":"2021","unstructured":"Xingxuan Zhang, Peng Cui, Renzhe Xu, Linjun Zhou, Yue He, and Zheyan Shen. 2021. Deep stable learning for out-of-distribution generalization. In CVPR. 5372\u20135382."},{"key":"e_1_3_1_93_2","first-page":"27965","article-title":"Shift-robust GNNS: Overcoming the limitations of localized graph training data","volume":"34","author":"Zhu Qi","year":"2021","unstructured":"Qi Zhu, Natalia Ponomareva, Jiawei Han, and Bryan Perozzi. 2021. Shift-robust GNNS: Overcoming the limitations of localized graph training data. Neural Inf. Process. 34 (2021), 27965\u201327977.","journal-title":"Neural Inf. Process."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3644392","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3644392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:48Z","timestamp":1750287048000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3644392"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,26]]},"references-count":92,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,6,30]]}},"alternative-id":["10.1145\/3644392"],"URL":"https:\/\/doi.org\/10.1145\/3644392","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,26]]},"assertion":[{"value":"2023-06-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}