{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:33:44Z","timestamp":1773246824890,"version":"3.50.1"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T00:00:00Z","timestamp":1739491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,2,28]]},"abstract":"<jats:p>\n            As Graph Neural Networks (GNNs) have been widely used in real-world applications, model explanations are required not only by users but also by legal regulations. However, simultaneously achieving high fidelity and low computational costs in generating explanations has been a challenge for current methods. In this work, we propose a framework of GNN explanation named\n            <jats:italic>L<\/jats:italic>\n            e\n            <jats:italic>A<\/jats:italic>\n            rn\n            <jats:italic>R<\/jats:italic>\n            emoval-based\n            <jats:italic>A<\/jats:italic>\n            ttribution (LARA) to address this problem. Specifically, we introduce removal-based attribution and demonstrate its substantiated link to interpretability fidelity theoretically and experimentally. The explainer in LARA learns to generate removal-based attribution which enables providing explanations with high fidelity. A strategy of subgraph sampling is designed in LARA to improve the scalability of the training process. In the deployment, LARA can efficiently generate the explanation through a feed-forward pass. We benchmark our approach with other state-of-the-art GNN explanation methods on six datasets. Results highlight the effectiveness of our framework regarding both efficiency and fidelity. In particular, LARA is 3.1\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            faster and achieves higher fidelity than the state-of-the-art method on the large dataset ogbn-arxiv (more than 160K nodes and 1M edges), showing its great potential in real-world applications. Our source code is available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/yaorong0921\/LARA\">https:\/\/github.com\/yaorong0921\/LARA<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3685678","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T14:56:56Z","timestamp":1723042616000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient GNN Explanation via Learning Removal-based Attribution"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6031-3741","authenticated-orcid":false,"given":"Yao","family":"Rong","sequence":"first","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3258-762X","authenticated-orcid":false,"given":"Guanchu","family":"Wang","sequence":"additional","affiliation":[{"name":"Rice University, Houston, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2574-0270","authenticated-orcid":false,"given":"Qizhang","family":"Feng","sequence":"additional","affiliation":[{"name":"Texas A&amp;M University, College Station, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9170-2424","authenticated-orcid":false,"given":"Ninghao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Georgia, Athens, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4335-1115","authenticated-orcid":false,"given":"Zirui","family":"Liu","sequence":"additional","affiliation":[{"name":"Rice University, Houston, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3146-4484","authenticated-orcid":false,"given":"Enkelejda","family":"Kasneci","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2234-3226","authenticated-orcid":false,"given":"Xia","family":"Hu","sequence":"additional","affiliation":[{"name":"Rice University, Houston, TX, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,2,14]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"7786","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"31","author":"Melis David Alvarez","year":"2018","unstructured":"David Alvarez Melis and Tommi Jaakkola. 2018. Towards robust interpretability with self-explaining neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 31, 7786\u20137795."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_3_2_4_2","first-page":"5644","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"34","author":"Bajaj Mohit","year":"2021","unstructured":"Mohit Bajaj, Lingyang Chu, Zi Yu Xue, Jian Pei, Lanjun Wang, Peter Cho-Ho Lam, and Yong Zhang. 2021. Robust counterfactual explanations on graph neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 34, 5644\u20135655."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.286.5439.509"},{"key":"e_1_3_2_6_2","first-page":"883","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Chen Jianbo","year":"2018","unstructured":"Jianbo Chen, Le Song, Martin Wainwright, and Michael Jordan. 2018. Learning to explain: An information-theoretic perspective on model interpretation. In Proceedings of the International Conference on Machine Learning. PMLR, 883\u2013892."},{"key":"e_1_3_2_7_2","volume-title":"Submitted to the 11th International Conference on Learning Representations","author":"Chuang Yu-Neng","year":"2023","unstructured":"Yu-Neng Chuang, Guanchu Wang, Fan Yang, Xuanting Cai, Tripathi Pushkar, and Xia Hu. 2023. CoRTX: Contrastive framework for real-time explanation. In Submitted to the 11th International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=L2MUOUp0beo under review."},{"key":"e_1_3_2_8_2","unstructured":"Yu-Neng Chuang Guanchu Wang Fan Yang Zirui Liu Xuanting Cai Mengnan Du and Xia Hu. 2023. Efficient XAI techniques: A taxonomic survey. arXiv:2302.03225. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.2302.03225"},{"key":"e_1_3_2_9_2","first-page":"209","article-title":"Explaining by removing: A unified framework for model explanation","volume":"22","author":"Covert Ian","year":"2021","unstructured":"Ian Covert, Scott M. Lundberg, and Su-In Lee. 2021. Explaining by removing: A unified framework for model explanation. Journal of Machine Learning Research 22 (2021), 209\u20131.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"e_1_3_2_11_2","first-page":"5376","article-title":"A comprehensive study on large-scale graph training: Benchmarking and rethinking","volume":"35","author":"Duan Keyu","year":"2022","unstructured":"Keyu Duan, Zirui Liu, Peihao Wang, Wenqing Zheng, Kaixiong Zhou, Tianlong Chen, Xia Hu, and Zhangyang Wang. 2022. A comprehensive study on large-scale graph training: Benchmarking and rethinking. Advances in Neural Information Processing Systems 35 (2022), 5376\u20135389.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86520-7_19"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"e_1_3_2_14_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Feng Qizhang","year":"2022","unstructured":"Qizhang Feng, Ninghao Liu, Fan Yang, Ruixiang Tang, Mengnan Du, and Xia Hu. 2022. DEGREE: Decomposition based explanation for graph neural networks. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=Ve0Wth3ptT_"},{"key":"e_1_3_2_15_2","unstructured":"Thorben Funke Megha Khosla and Avishek Anand. 2021. Hard masking for explaining graph neural networks. (2021). Retrieved from https:\/\/openreview.net\/forum?id=uDN8pRAdsoC"},{"key":"e_1_3_2_16_2","unstructured":"EU GDPR. 2016. Recital 71. Retrieved from https:\/\/www.privacy-regulation.eu\/en\/r71.htm"},{"key":"e_1_3_2_17_2","first-page":"9737","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"32","author":"Hooker Sara","year":"2019","unstructured":"Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, and Been Kim. 2019. A benchmark for interpretability methods in deep neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32, 9737\u20139748."},{"key":"e_1_3_2_18_2","first-page":"22118","volume-title":"Advances in Neural Information Processing Systems","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. In Advances in Neural Information Processing Systems, Vol. 33, 22118\u201322133."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3187455"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29157"},{"key":"e_1_3_2_21_2","first-page":"1459","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics.","author":"Jethani Neil","year":"2021","unstructured":"Neil Jethani, Mukund Sudarshan, Yindalon Aphinyanaphongs, and Rajesh Ranganath. 2021. Have we learned to explain?: How interpretability methods can learn to encode predictions in their interpretations.. In Proceedings of the International Conference on Artificial Intelligence and Statistics. PMLR, 1459\u20131467."},{"key":"e_1_3_2_22_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Jethani Neil","year":"2021","unstructured":"Neil Jethani, Mukund Sudarshan, Ian Connick Covert, Su-In Lee, and Rajesh Ranganath. 2021. FastSHAP: Real-Time shapley value estimation. In Proceedings of the International Conference on Learning Representations. DOI: https:\/\/openreview.net\/forum?id=Zq2G_VTV53T"},{"key":"e_1_3_2_23_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_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01336"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-6054-2_7"},{"key":"e_1_3_2_26_2","first-page":"21951","volume-title":"International Conference on Machine Learning","author":"Liu Zirui","unstructured":"Zirui Liu, Shengyuan Chen, Kaixiong Zhou, Daochen Zha, Xiao Huang, and Xia Hu. 2023. RSC: Accelerating graph neural networks training via randomized sparse computations. In International Conference on Machine Learning, 21951\u201321968."},{"key":"e_1_3_2_27_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Liu Zirui","year":"2022","unstructured":"Zirui Liu, Kaixiong Zhou, Fan Yang, Li Li, Rui Chen, and Xia Hu. 2022. EXACT: Scalable graph neural networks training via extreme activation compression. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=vkaMaq95_rX"},{"key":"e_1_3_2_28_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Lu Shengyao","year":"2024","unstructured":"Shengyao Lu, Keith G Mills, Jiao He, Bang Liu, and Di Niu. 2024. GOAt: Explaining graph neural networks via graph output attribution. In Proceedings of the International Conference on Learning Representations (2024). Retrieved from https:\/\/openreview.net\/forum?id=2Q8TZWAHv4"},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"30","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_2_30_2","first-page":"19620","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","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. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 19620\u201319631."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21499"},{"key":"e_1_3_2_32_2","first-page":"3111","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"26","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 26, 3111\u20133119."},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the British Machine Vision Conference.","author":"Petsiuk Vitali","year":"2018","unstructured":"Vitali Petsiuk, Abir Das, and Kate Saenko. 2018. Rise: Randomized input sampling for explanation of black-box models. In Proceedings of the British Machine Vision Conference."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01103"},{"key":"e_1_3_2_35_2","first-page":"18770","volume-title":"International Conference on Machine Learning","author":"Rong Yao","year":"2022","unstructured":"Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, and Enkelejda Kasneci. 2022. A consistent and efficient evaluation strategy for attribution methods. In International Conference on Machine Learning, 18770\u201318795."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115452"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6064"},{"key":"e_1_3_2_38_2","first-page":"12225","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"33","author":"Vu Minh","year":"2020","unstructured":"Minh Vu and My T. Thai. 2020. Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 12225\u201312235."},{"key":"e_1_3_2_39_2","first-page":"22576","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Wang Guanchu","year":"2022","unstructured":"Guanchu Wang, Yu-Neng Chuang, Mengnan Du, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai, and Xia Hu. 2022. Accelerating shapley explanation via contributive cooperator selection. In Proceedings of the International Conference on Machine Learning. PMLR, 22576\u201322590."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170302"},{"key":"e_1_3_2_41_2","first-page":"37511","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Wu Fang","year":"2023","unstructured":"Fang Wu, Siyuan Li, Xurui Jin, Yinghui Jiang, Dragomir Radev, Zhangming Niu, and Stan Z. Li. 2023. Rethinking explaining graph neural networks via non-parametric subgraph matching. In Proceedings of the International Conference on Machine Learning. PMLR, 37511\u201337523."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_44_2","first-page":"38301","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Xiong Ping","year":"2023","unstructured":"Ping Xiong, Thomas Schnake, Michael Gastegger, Gr\u00e9goire Montavon, Klaus Robert Muller, and Shinichi Nakajima. 2023. Relevant walk search for explaining graph neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 38301\u201338324."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00537"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599289"},{"key":"e_1_3_2_47_2","first-page":"10967","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"32","author":"Yeh Chih-Kuan","year":"2019","unstructured":"Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Suggala, David I. Inouye, and Pradeep K. Ravikumar. 2019. On the (in) fidelity and sensitivity of explanations. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32, 10967\u201310978."},{"key":"e_1_3_2_48_2","first-page":"9244","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"32","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 Proceedings of the Advances in Neural Information Processing Systems, Vol. 32, 9244\u20139255."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599413"},{"key":"e_1_3_2_50_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."},{"issue":"2","key":"e_1_3_2_51_2","first-page":"5782","article-title":"Explainability in graph neural networks: A taxonomic survey","volume":"45","author":"Yuan Hao","year":"2022","unstructured":"Hao Yuan, Haiyang Yu, Shurui Gui, and Shuiwang Ji. 2022. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 2 (2022), 5782\u20135799.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_52_2","unstructured":"Hanqing Zeng Hongkuan Zhou Ajitesh Srivastava Rajgopal Kannan and Viktor Prasanna. 2020. Graphsaint: Graph sampling based inductive learning method. In International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=BJe8pkHFw"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599435"},{"key":"e_1_3_2_54_2","first-page":"19810","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"35","author":"Zhang Shichang","year":"2022","unstructured":"Shichang Zhang, Yozen Liu, Neil Shah, and Yizhou Sun. 2022. GStarX: Explaining graph neural networks with structure-aware cooperative games. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 35, 19810\u201319823."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462562"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10050593"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3685678","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3685678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:26Z","timestamp":1750295846000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3685678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,14]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2,28]]}},"alternative-id":["10.1145\/3685678"],"URL":"https:\/\/doi.org\/10.1145\/3685678","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,14]]},"assertion":[{"value":"2023-09-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}