{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:23:45Z","timestamp":1776889425960,"version":"3.51.2"},"reference-count":130,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:00:00Z","timestamp":1736380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"MUR PNRR project FAIR - Future AI Research","award":["PE00000013"],"award-info":[{"award-number":["PE00000013"]}]},{"DOI":"10.13039\/100031478","name":"NextGenerationEU","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100031478","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100018693","name":"Horizon Europe Programme","doi-asserted-by":"crossref","award":["101120237 - ELIAS and 101120763 - TANGO"],"award-info":[{"award-number":["101120237 - ELIAS and 101120763 - TANGO"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"crossref"}]},{"name":"European Union\u2019s Horizon research and innovation","award":["101103026"],"award-info":[{"award-number":["101103026"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2025,5,31]]},"abstract":"<jats:p>Following a fast initial breakthrough in graph-based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process. GNN explainers have started to emerge in recent years, with a multitude of methods both novel or adapted from other domains. To sort out this plethora of alternative approaches, several studies have benchmarked the performance of different explainers in terms of various explainability metrics. However, these earlier works make no attempts at providing insights into why different GNN architectures are more or less explainable or which explainer should be preferred in a given setting. In this survey we fill these gaps by devising a systematic experimental study, which tests 12 explainers on eight representative message-passing architectures trained on six carefully designed graph and node classification datasets. With our results we provide key insights on the choice and applicability of GNN explainers, we isolate key components that make them usable and successful and provide recommendations on how to avoid common interpretation pitfalls. We conclude by highlighting open questions and directions of possible future research.<\/jats:p>","DOI":"10.1145\/3696444","type":"journal-article","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T07:34:27Z","timestamp":1727163267000},"page":"1-37","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Explaining the Explainers in Graph Neural Networks: a Comparative Study"],"prefix":"10.1145","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0337-1838","authenticated-orcid":false,"given":"Antonio","family":"Longa","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy and DISI, University of Trento, Trento, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3418-0585","authenticated-orcid":false,"given":"Steve","family":"Azzolin","sequence":"additional","affiliation":[{"name":"DISI, University of Trento, Trento, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6959-1070","authenticated-orcid":false,"given":"Gabriele","family":"Santin","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-3666","authenticated-orcid":false,"given":"Giulia","family":"Cencetti","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0540-5053","authenticated-orcid":false,"given":"Pietro","family":"Lio","sequence":"additional","affiliation":[{"name":"Cambridge University, Cambridge, United Kingdom of Great Britain and Northern Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1275-2333","authenticated-orcid":false,"given":"Bruno","family":"Lepri","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2765-5395","authenticated-orcid":false,"given":"Andrea","family":"Passerini","sequence":"additional","affiliation":[{"name":"DISI, University of Trento, Trento, Italy"}]}],"member":"320","published-online":{"date-parts":[[2025,1,9]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"crossref","unstructured":"Chirag Agarwal Owen Queen Himabindu Lakkaraju and Marinka Zitnik. 2023. Evaluating explainability for graph neural networks. Scientific Data 10 1 (2023) 144.","DOI":"10.1038\/s41597-023-01974-x"},{"key":"e_1_3_3_3_2","first-page":"8969","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Agarwal Chirag","year":"2022","unstructured":"Chirag Agarwal, Marinka Zitnik, and Himabindu Lakkaraju. 2022. Probing gnn explainers: A rigorous theoretical and empirical analysis of gnn explanation methods. In International Conference on Artificial Intelligence and Statistics. PMLR, 8969\u20138996."},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11010060"},{"key":"e_1_3_3_5_2","volume-title":"Advances in Neural Information Processing Systems","author":"Atwood James","year":"2016","unstructured":"James Atwood and Don Towsley. 2016. Diffusion-convolutional neural networks. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett (Eds.), Vol. 29. Curran Associates, Inc."},{"key":"e_1_3_3_6_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Azzolin Steve","year":"2022","unstructured":"Steve Azzolin, Antonio Longa, Pietro Barbiero, Pietro Lio, and Andrea Passerini. 2022. Global explainability of GNNs via logic combination of learned concepts. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1859912"},{"key":"e_1_3_3_8_2","unstructured":"Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations (ICLR\u201915)."},{"key":"e_1_3_3_9_2","unstructured":"Federico Baldassarre and Hossein Azizpour. 2019. Explainability techniques for graph convolutional networks. In International Conference on Machine Learning (ICML) Workshops 2019 Workshop on Learning and Reasoning with Graph-Structured Representations."},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.286.5439.509"},{"key":"e_1_3_3_11_2","unstructured":"Sourya Basu Jose Gallego-Posada Francesco Vigan\u00f2 James Rowbottom and Taco Cohen. 2022. Equivariant mesh attention networks. Transactions on Machine Learning Research 2022. Expert Certification."},{"key":"e_1_3_3_12_2","first-page":"874","volume-title":"International Conference on Machine Learning","author":"Bianchi Filippo Maria","year":"2020","unstructured":"Filippo Maria Bianchi, Daniele Grattarola, and Cesare Alippi. 2020. Spectral clustering with graph neural networks for graph pooling. In International Conference on Machine Learning. PMLR, 874\u2013883."},{"issue":"1","key":"e_1_3_3_13_2","first-page":"i47\u2013i56","article-title":"Protein function prediction via graph kernels","volume":"21","author":"Borgwardt Karsten M.","year":"2005","unstructured":"Karsten M. Borgwardt, Cheng Soon Ong, Stefan Sch\u00f6nauer, S. V. N. Vishwanathan, Alex J. Smola, and Hans-Peter Kriegel. 2005. Protein function prediction via graph kernels. Bioinformatics 21, suppl_1 (2005), i47\u2013i56.","journal-title":"Bioinformatics"},{"key":"e_1_3_3_14_2","unstructured":"C\u0103t\u0103lina Cangea Petar Veli\u010dkovi\u0107 Nikola Jovanovi\u0107 Thomas Kipf and Pietro Li\u00f2. 2018. Towards sparse hierarchical graph classifiers. arXiv preprint arXiv:1811.01287."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/595"},{"key":"e_1_3_3_16_2","volume-title":"Proceedings of the 2nd Learning on Graphs Conference","author":"Christiansen Marc","year":"2023","unstructured":"Marc Christiansen, Lea Villadsen, Zhiqiang Zhong, Stefano Teso, and Davide Mottin. 2023. How faithful are self-explainable GNNs? In Proceedings of the 2nd Learning on Graphs Conference."},{"key":"e_1_3_3_17_2","unstructured":"Dan C. Cire\u015fan Ueli Meier Jonathan Masci Luca M Gambardella and J\u00fcrgen Schmidhuber. 2011. High-performance neural networks for visual object classification."},{"key":"e_1_3_3_18_2","unstructured":"Kevin Clark Minh-Thang Luong Quoc V. Le and Christopher D. Manning. 2020. Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555."},{"key":"e_1_3_3_19_2","unstructured":"Enyan Dai Tianxiang Zhao Huaisheng Zhu Jun Xu Zhimeng Guo Hui Liu Jiliang Tang and Suhang Wang. 2024. A Comprehensive survey on trustworthy graph neural networks: Privacy robustness fairness and explainability. Machine Intelligence Research (2024) 1\u201351."},{"key":"e_1_3_3_20_2","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"Defferrard Micha\u00ebl","year":"2016","unstructured":"Micha\u00ebl Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in Neural Information Processing Systems 29 (2016).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Jay DeYoung Sarthak Jain Nazneen Fatema Rajani Eric Lehman Caiming Xiong Richard Socher and Byron C. Wallace. 2020. ERASER: A benchmark to evaluate rationalized NLP models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 4443\u20134458.","DOI":"10.18653\/v1\/2020.acl-main.408"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557353"},{"key":"e_1_3_3_23_2","unstructured":"Vijay Prakash Dwivedi and Xavier Bresson. 2020. A generalization of transformer networks to graphs. AAAI Workshop on Deep Learning on Graphs: Methods and Applications."},{"issue":"1","key":"e_1_3_3_24_2","first-page":"290","article-title":"On random graphs I","volume":"6","author":"Erd\u0151s Paul","year":"1959","unstructured":"Paul Erd\u0151s and Alfr\u00e9d R\u00e9nyi. 1959. On random graphs I. Publicationes Mathematicae 6, 1 (1959), 290\u2013297.","journal-title":"Publicationes Mathematicae"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467283"},{"key":"e_1_3_3_26_2","unstructured":"Xiang Fu Tian Xie Nathan J. Rebello Bradley Olsen and Tommi Jaakkola. 2023. Simulate time-integrated coarse-grained molecular dynamics with geometric machine learning. Transactions on Machine Learning Research."},{"key":"e_1_3_3_27_2","unstructured":"Thorben Funke Megha Khosla and Avishek Anand. 2021. Hard Masking for Explaining Graph Neural Networks."},{"key":"e_1_3_3_28_2","article-title":"Z ORRO: Valid, sparse, and stable explanations in graph neural networks","author":"Funke Thorben","year":"2022","unstructured":"Thorben Funke, Megha Khosla, Mandeep Rathee, and Avishek Anand. 2022. Z ORRO: Valid, sparse, and stable explanations in graph neural networks. IEEE Transactions on Knowledge and Data Engineering (2022).","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3105544"},{"key":"e_1_3_3_30_2","unstructured":"Johannes Gasteiger Stefan Wei\u00dfenberger and Stephan G\u00fcnnemann. 2022. Diffusion Improves Graph Learning."},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Dobrik Georgiev and Pietro Li\u00f2. 2020. Neural Bipartite Matching. 10.48550\/ARXIV.2005.11304","DOI":"10.48550\/ARXIV.2005.11304"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305512"},{"key":"e_1_3_3_33_2","first-page":"1263","volume-title":"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 International Conference on Machine Learning. PMLR, 1263\u20131272."},{"key":"e_1_3_3_34_2","volume-title":"Learning on Graphs Conference","author":"Giunchiglia Valentina","year":"2022","unstructured":"Valentina Giunchiglia, Chirag Varun Shukla, Guadalupe Gonzalez, and Chirag Agarwal. 2022. Towards training GNNs using explanation directed message passing. In Learning on Graphs Conference. PMLR, 28\u20131."},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"e_1_3_3_37_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. Advances in Neural Information Processing Systems 30 (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2010.04.005"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7_11"},{"key":"e_1_3_3_40_2","volume-title":"Convolution Kernels on Discrete Structures","author":"Haussler David","year":"1999","unstructured":"David Haussler et\u00a0al. 1999. Convolution Kernels on Discrete Structures. Technical Report. Department of Computer Science, University of California."},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_42_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. Advances in Neural Information Processing Systems 33 (2020), 22118\u201322133.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3187455"},{"key":"e_1_3_3_44_2","first-page":"16727","article-title":"Learning equivariant energy based models with equivariant stein variational gradient descent","volume":"34","author":"Jaini Priyank","year":"2021","unstructured":"Priyank Jaini, Lars Holdijk, and Max Welling. 2021. Learning equivariant energy based models with equivariant stein variational gradient descent. Advances in Neural Information Processing Systems 34 (2021), 16727\u201316737.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_45_2","article-title":"Information retrieval test collections","author":"Jones K. Sparck","year":"1976","unstructured":"K. Sparck Jones and Cornelis Joost Van Rijsbergen. 1976. Information retrieval test collections. J. Document. (1976).","journal-title":"J. Document."},{"key":"e_1_3_3_46_2","unstructured":"Jaykumar Kakkad Jaspal Jannu Kartik Sharma Charu Aggarwal and Sourav Medya. 2023. A survey on explainability of graph neural networks. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering."},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-022-00590-y"},{"key":"e_1_3_3_48_2","unstructured":"Megha Khosla. 2022. Privacy and transparency in graph machine learning: A unified perspective. arXiv preprint arXiv:2207.10896."},{"key":"e_1_3_3_49_2","unstructured":"Jinwoo Kim Tien Dat Nguyen Seonwoo Min Sungjun Cho Moontae Lee Honglak Lee and Seunghoon Hong. 2022. Pure transformers are powerful graph learners. Advances in Neural Information Processing Systems 35 (2022) 14582\u201314595."},{"key":"e_1_3_3_50_2","unstructured":"Thomas N. Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations."},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970"},{"key":"e_1_3_3_53_2","first-page":"3734","volume-title":"International Conference on Machine Learning","author":"Lee Junhyun","year":"2019","unstructured":"Junhyun Lee, Inyeop Lee, and Jaewoo Kang. 2019. Self-attention graph pooling. In International Conference on Machine Learning. PMLR, 3734\u20133743."},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.3390\/app12084089"},{"key":"e_1_3_3_55_2","article-title":"Higher-order attribute-enhancing heterogeneous graph neural networks","author":"Li Jianxin","year":"2021","unstructured":"Jianxin Li, Hao Peng, Yuwei Cao, Yingtong Dou, Hekai Zhang, Philip Yu, and Lifang He. 2021. Higher-order attribute-enhancing heterogeneous graph neural networks. IEEE Transactions on Knowledge and Data Engineering (2021).","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_3_56_2","unstructured":"Peibo Li Yixing Yang Maurice Pagnucco and Yang Song. 2022. Explainability in graph neural networks: An experimental survey. arXiv preprint arXiv:2203.09258."},{"key":"e_1_3_3_57_2","unstructured":"Wei Li Ruxuan Li Yuzhe Ma Siu On Chan David Pan and Bei Yu. 2022. Rethinking graph neural networks for the graph coloring problem."},{"key":"e_1_3_3_58_2","unstructured":"Wenqian Li Yinchuan Li Zhigang Li Jianye Hao and Yan Pang. 2023. DAG Matters! GFlowNets enhanced explainer for graph neural networks."},{"key":"e_1_3_3_59_2","unstructured":"Yiqiao Li Jianlong Zhou Sunny Verma and Fang Chen. 2022. A survey of explainable graph neural networks: Taxonomy and evaluation metrics."},{"key":"e_1_3_3_60_2","first-page":"6666","volume-title":"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 International Conference on Machine Learning. PMLR, 6666\u20136679."},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01336"},{"key":"e_1_3_3_62_2","unstructured":"Yang Liu Yao Zhang Yixin Wang Feng Hou Jin Yuan Jiang Tian Yang Zhang Zhongchao Shi Jianping Fan and Zhiqiang He. 2021. A survey of visual transformers. IEEE Transactions on Neural Networks and Learning Systems."},{"key":"e_1_3_3_63_2","article-title":"Graph neural networks for temporal graphs: State of the art, open challenges, and opportunities","author":"Longa Antonio","year":"2023","unstructured":"Antonio Longa, Veronica Lachi, Gabriele Santin, Monica Bianchini, Bruno Lepri, Pietro Lio, franco scarselli, and Andrea Passerini. 2023. Graph neural networks for temporal graphs: State of the art, open challenges, and opportunities. Transactions on Machine Learning Research (2023).","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_3_3_64_2","first-page":"4499","volume-title":"Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research)","volume":"151","author":"Lucic Ana","year":"2022","unstructured":"Ana Lucic, Maartje A. Ter Hoeve, Gabriele Tolomei, Maarten De Rijke, and Fabrizio Silvestri. 2022. CF-GNNExplainer: Counterfactual explanations for graph neural networks. In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research), Gustau Camps-Valls, Francisco J. R. Ruiz, and Isabel Valera (Eds.), Vol. 151. PMLR, 4499\u20134511. https:\/\/proceedings.mlr.press\/v151\/lucic22a.html"},{"key":"e_1_3_3_65_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_3_66_2","doi-asserted-by":"publisher","DOI":"10.14778\/3611479.3611538"},{"key":"e_1_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00123-9_52"},{"key":"e_1_3_3_68_2","first-page":"15524","volume-title":"International Conference on Machine Learning","author":"Miao Siqi","year":"2022","unstructured":"Siqi Miao, Mia Liu, and Pan Li. 2022. Interpretable and generalizable graph learning via stochastic attention mechanism. In International Conference on Machine Learning. PMLR, 15524\u201315543."},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.001"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"e_1_3_3_71_2","unstructured":"Peter M\u00fcller Lukas Faber Karolis Martinkus and Roger Wattenhofer. 2024. GraphChef: Decision-tree recipes to explain graph neural networks. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645674"},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-syb.2020.0004"},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01103"},{"key":"e_1_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014731"},{"issue":"140","key":"e_1_3_3_76_2","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer.","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J Liu, et\u00a0al. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140 (2020), 1\u201367.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3222618"},{"key":"e_1_3_3_78_2","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125."},{"key":"e_1_3_3_79_2","unstructured":"Ladislav Ramp\u00e1\u0161ek Mikhail Galkin Vijay Prakash Dwivedi Anh Tuan Luu Guy Wolf and Dominique Beaini. 2022. Recipe for a general powerful scalable graph transformer. Advances in Neural Information Processing Systems 35 (2022) 14501\u201314515."},{"key":"e_1_3_3_80_2","unstructured":"Mandeep Rathee Thorben Funke Avishek Anand and Megha Khosla. 2022. BAGEL: A benchmark for assessing graph neural network explanations. arXiv preprint arXiv:2206.13983."},{"key":"e_1_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_3_82_2","first-page":"581","volume-title":"Proceedings of the 13th Language Resources and Evaluation Conference","author":"Roccabruna Gabriel","year":"2022","unstructured":"Gabriel Roccabruna, Steve Azzolin, and Giuseppe Riccardi. 2022. Multi-source multi-domain sentiment analysis with BERT-based models. In Proceedings of the 13th Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 581\u2013589."},{"key":"e_1_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9049000"},{"key":"e_1_3_3_84_2","volume-title":"ICML\u201920 Workshop on Graph Representation Learning","author":"Rossi Emanuele","year":"2020","unstructured":"Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael Bronstein. 2020. Temporal graph networks for deep learning on dynamic graphs. In ICML\u201920 Workshop on Graph Representation Learning."},{"key":"e_1_3_3_85_2","first-page":"5898","article-title":"Evaluating attribution for graph neural networks","volume":"33","author":"Sanchez-Lengeling Benjamin","year":"2020","unstructured":"Benjamin Sanchez-Lengeling, Jennifer Wei, Brian Lee, Emily Reif, Peter Wang, Wesley Qian, Kevin McCloskey, Lucy Colwell, and Alexander Wiltschko. 2020. Evaluating attribution for graph neural networks. Advances in Neural Information Processing Systems 33 (2020), 5898\u20135910.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_86_2","unstructured":"Michael Sejr Schlichtkrull Nicola De Cao and Ivan Titov. 2020. Interpreting graph neural networks for nlp with differentiable edge masking. In International Conference on Learning Representations."},{"key":"e_1_3_3_87_2","article-title":"Higher-order explanations of graph neural networks via relevant walks","author":"Schnake Thomas","year":"2021","unstructured":"Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schutt, Klaus-Robert M\u00fcller, and Gr\u00e9goire Montavon. 2021. Higher-order explanations of graph neural networks via relevant walks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_3_88_2","doi-asserted-by":"crossref","unstructured":"Robert Schwarzenberg Marc H\u00fcbner David Harbecke Christoph Alt and Leonhard Hennig. 2019. Layerwise relevance visualization in convolutional text graph classifiers. In Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13). 58\u201362.","DOI":"10.18653\/v1\/D19-5308"},{"key":"e_1_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24258-9_24"},{"key":"e_1_3_3_90_2","volume-title":"International Conference on Learning Representations","author":"Selsam Daniel","year":"2019","unstructured":"Daniel Selsam, Matthew Lamm, Benedikt B\u00fcnz, Percy Liang, Leonardo de Moura, and David L. Dill. 2019. Learning a SAT solver from single-bit supervision. In International Conference on Learning Representations."},{"key":"e_1_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/1055\/1\/012119"},{"key":"e_1_3_3_93_2","doi-asserted-by":"crossref","unstructured":"Giuseppe Serra and Mathias Niepert. 2024. L2XGNN: Learning to explain graph neural networks.","DOI":"10.1007\/s10994-024-06576-1"},{"key":"e_1_3_3_94_2","first-page":"22523","volume-title":"Advances in Neural Information Processing Systems","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. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 22523\u201322533."},{"issue":"9","key":"e_1_3_3_95_2","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 12, 9 (2011).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43418-1_7"},{"key":"e_1_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"e_1_3_3_98_2","unstructured":"Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2014. Deep inside convolutional networks: Visualising image classification models and saliency maps. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_99_2","unstructured":"Indro Spinelli Simone Scardapane and Aurelio Uncini. 2022. A meta-learning approach for training explainable graph neural networks. IEEE Transactions on Neural Networks and Learning Systems."},{"key":"e_1_3_3_100_2","unstructured":"Jost Tobias Springenberg Alexey Dosovitskiy Thomas Brox and Martin Riedmiller. 2015. Striving for simplicity: The all convolutional net. In ICLR (workshop track)."},{"key":"e_1_3_3_101_2","first-page":"3319","volume-title":"International Conference on Machine Learning","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International Conference on Machine Learning. PMLR, 3319\u20133328."},{"key":"e_1_3_3_102_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_103_2","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations."},{"key":"e_1_3_3_104_2","unstructured":"Oriol Vinyals Samy Bengio and Manjunath Kudlur. 2015. Order matters: Sequence to sequence for sets. arXiv preprint arXiv:1511.06391."},{"key":"e_1_3_3_105_2","first-page":"12225","article-title":"Pgm-explainer: Probabilistic graphical model explanations for graph neural networks","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. Advances in Neural Information Processing Systems 33 (2020), 12225\u201312235.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_106_2","unstructured":"Rui Wang Robin Walters and Rose Yu. 2022. Approximately equivariant networks for imperfectly symmetric dynamics. In International Conference on Machine Learning. PMLR 23078\u201323091."},{"key":"e_1_3_3_107_2","article-title":"NeuroComb: Improving SAT solving with graph neural networks","author":"Wang Wenxi","year":"2021","unstructured":"Wenxi Wang, Yang Hu, Mohit Tiwari, Sarfraz Khurshid, Kenneth McMillan, and Risto Miikkulainen. 2021. NeuroComb: Improving SAT solving with graph neural networks. arXiv:2110.14053.","journal-title":"arXiv:"},{"key":"e_1_3_3_108_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wang Xiaoqi","year":"2022","unstructured":"Xiaoqi Wang and Han Wei Shen. 2022. GNNInterpreter: A probabilistic generative model-level explanation for graph neural networks. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_109_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang Xiaoqi","year":"2024","unstructured":"Xiaoqi Wang and Han Wei Shen. 2024. GNNBoundary: Towards explaining graph neural networks through the lens of decision boundaries. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170302"},{"issue":"9","key":"e_1_3_3_111_2","first-page":"12","article-title":"The reduction of a graph to canonical form and the algebra which appears therein","volume":"2","author":"Weisfeiler Boris","year":"1968","unstructured":"Boris Weisfeiler and Andrei Leman. 1968. The reduction of a graph to canonical form and the algebra which appears therein. NTI, Series 2, 9 (1968), 12\u201316.","journal-title":"NTI, Series"},{"key":"e_1_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00868"},{"key":"e_1_3_3_113_2","first-page":"2048","volume-title":"International Conference on Machine Learning","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International Conference on Machine Learning. PMLR, 2048\u20132057."},{"key":"e_1_3_3_114_2","unstructured":"Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2018. How powerful are graph neural networks? In International Conference on Learning Representations."},{"key":"e_1_3_3_115_2","article-title":"Gnnexplainer: Generating explanations for graph neural networks","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. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_116_2","article-title":"Hierarchical graph representation learning with differentiable pooling","volume":"31","author":"Ying Zhitao","year":"2018","unstructured":"Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, and Jure Leskovec. 2018. Hierarchical graph representation learning with differentiable pooling. Advances in Neural Information Processing Systems 31 (2018).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_117_2","unstructured":"Zhaoning Yu and Hongyang Gao. 2024. MAGE: Model-level graph neural networks explanations via motif-based graph generation. arXiv preprint arXiv:2405.12519."},{"key":"e_1_3_3_118_2","volume-title":"International Conference on Learning Representations","author":"Yuan Hao","year":"2020","unstructured":"Hao Yuan and Shuiwang Ji. 2020. StructPool: Structured graph pooling via conditional random fields. In International Conference on Learning Representations."},{"key":"e_1_3_3_119_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"issue":"5","key":"e_1_3_3_120_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, 5 (2022), 5782\u20135799.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_3_121_2","first-page":"12241","volume-title":"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 International Conference on Machine Learning. PMLR, 12241\u201312252."},{"key":"e_1_3_3_122_2","article-title":"Graph transformer networks","volume":"32","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo J Kim. 2019. Graph transformer networks. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_123_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_3_3_124_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"e_1_3_3_125_2","unstructured":"Ruochi Zhang Yuesong Zou and Jian Ma. 2019. Hyper-SAGNN: A self-attention based graph neural network for hypergraphs. In International Conference on Learning Representations."},{"key":"e_1_3_3_126_2","volume-title":"International Conference on Learning Representations","author":"Zhang Yuyu","year":"2020","unstructured":"Yuyu Zhang, Xinshi Chen, Yuan Yang, Arun Ramamurthy, Bo Li, Yuan Qi, and Le Song. 2020. Efficient probabilistic logic reasoning with graph neural networks. In International Conference on Learning Representations."},{"key":"e_1_3_3_127_2","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462562"},{"key":"e_1_3_3_128_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20898"},{"key":"e_1_3_3_129_2","unstructured":"Tianxiang Zhao Dongsheng Luo Xiang Zhang and Suhang Wang. 2022. On consistency in graph neural network interpretation. arXiv preprint arXiv:2205.13733."},{"key":"e_1_3_3_130_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_3_131_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696444","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:13Z","timestamp":1750295413000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,9]]},"references-count":130,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5,31]]}},"alternative-id":["10.1145\/3696444"],"URL":"https:\/\/doi.org\/10.1145\/3696444","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,9]]},"assertion":[{"value":"2022-10-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}