{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:21:25Z","timestamp":1784737285741,"version":"3.55.0"},"reference-count":49,"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"}],"funder":[{"name":"National Science Foundation","award":["IIS-1909702"],"award-info":[{"award-number":["IIS-1909702"]}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"crossref","award":["W911NF21-1-0198"],"award-info":[{"award-number":["W911NF21-1-0198"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"crossref"}]}],"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            Graph Neural Networks (GNNs) have shown great ability in modeling graph-structured data for various domains. However, GNNs are known as black-box models that lack interpretability. Without understanding their inner working, we cannot fully trust them, which largely limits their adoption in high-stake scenarios. Though some initial efforts have been taken to interpret the predictions of GNNs, they mainly focus on providing\n            <jats:italic>post hoc<\/jats:italic>\n            explanations using an additional explainer, which could misrepresent the true inner working mechanism of the target GNN. The works on self-explainable GNNs are rather limited. Therefore, we study a novel problem of learning prototype-based self-explainable GNNs that can simultaneously give accurate predictions and prototype-based explanations on predictions. We design a framework which can learn prototype graphs that capture representative patterns of each class as class-level explanations. The learned prototypes are also used to simultaneously make prediction for a test instance and provide instance-level explanation. Extensive experiments on real-world and synthetic datasets show the effectiveness of the proposed framework for both prediction accuracy and explanation quality.\n          <\/jats:p>","DOI":"10.1145\/3689647","type":"journal-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T14:29:30Z","timestamp":1725028170000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Towards Prototype-Based Self-Explainable Graph Neural Network"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9715-0280","authenticated-orcid":false,"given":"Enyan","family":"Dai","sequence":"first","affiliation":[{"name":"The Pennsylvania State University, University Park, PA, USA and The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3448-4878","authenticated-orcid":false,"given":"Suhang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, University Park, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,2,14]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"7786","volume-title":"Proceedings of Advances in neural information processing systems 31 (NeurIPS 2018)","author":"Alvarez-Melis D.","year":"2018","unstructured":"D. Alvarez-Melis and T. S. Jaakkola. 2018. Towards robust interpretability with self-explaining neural networks. In Proceedings of Advances in neural information processing systems 31 (NeurIPS 2018), 7786\u20137795."},{"key":"e_1_3_1_3_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Azzolin S.","year":"2023","unstructured":"S. Azzolin, A. Longa, P. Barbiero, P. Lio, and A. Passerini. 2023. Global explainability of GNNs via logic combination of learned concepts. In Proceedings of the 11th International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=OTbRTIY4YS"},{"key":"e_1_3_1_4_2","first-page":"384","volume-title":"Proceedings of the 12th ACM International Conference on Web Search and Data Mining (WSDM \u201919)","author":"Bai Y.","year":"2019","unstructured":"Y. Bai, H. Ding, S. Bian, T. Chen, Y. Sun, and W. Wang. 2019. SimGNN: A neural network approach to fast graph similarity computation. In Proceedings of the 12th ACM International Conference on Web Search and Data Mining (WSDM \u201919), 384\u2013392."},{"key":"e_1_3_1_5_2","first-page":"10772","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)","author":"Baldassarre F.","year":"2019","unstructured":"F. Baldassarre and H. Azizpour. 2019. Explainability techniques for graph convolutional networks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), 10772\u201310781."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.039"},{"key":"e_1_3_1_7_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR \u201914)","author":"Bruna J.","year":"2014","unstructured":"J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun. 2014. Spectral networks and locally connected networks on graphs. In Proceedings of the International Conference on Learning Representations (ICLR \u201914)."},{"key":"e_1_3_1_8_2","first-page":"8928","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"32","author":"Chen C.","year":"2019","unstructured":"C. Chen, O. Li, D. Tao, A. Barnett, C. Rudin, and J. K. Su. 2019. This looks like that: deep learning for interpretable image recognition. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32, 8928\u20138939."},{"key":"e_1_3_1_9_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR \u201918)","author":"Chen J.","year":"2018","unstructured":"J. Chen, T. Ma, and C. Xiao. 2018. FastGCN: Fast learning with graph convolutional networks via importance sampling. In Proceedings of the International Conference on Learning Representations (ICLR \u201918)."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525099"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482306"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220099"},{"key":"e_1_3_1_14_2","first-page":"1024","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS \u201917)","author":"Hamilton W.","year":"2017","unstructured":"W. Hamilton, Z. Ying, and J. Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS \u201917), 1024\u20131034."},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1145\/3306618.3314273","volume-title":"Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society","author":"Hind M.","year":"2019","unstructured":"M. Hind, D. Wei, M. Campbell, N. C. F. Codella, A. Dhurandhar, A. Mojsilovi\u0107, K. N. Ramamurthy, and K. R. Varshney. 2019. TED: Teaching AI to explain its decisions. In Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, 123\u2013129."},{"key":"e_1_3_1_16_2","first-page":"6968","article-title":"Graphlime: Local interpretable model explanations for graph neural networks","author":"Huang Q.","year":"2020","unstructured":"Q. Huang, M. Yamada, Y. Tian, D. Singh, D. Yin, and Y. Chang. 2020. Graphlime: Local interpretable model explanations for graph neural networks. IEEE Transations on Knowledge and Data Engineering, 6968\u20136972.","journal-title":"IEEE Transations on Knowledge and Data Engineering"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00479-8"},{"key":"e_1_3_1_18_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kim D.","year":"2021","unstructured":"D. Kim and A. Oh. 2021. How to find your friendly neighborhood: Graph attention design with self-supervision. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_19_2","volume-title":"Proceedings of 5th International Conference on Learning Representations (ICLR 2017)","author":"Kipf T. N.","year":"2017","unstructured":"T. N. Kipf and M. Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of 5th International Conference on Learning Representations (ICLR 2017). Retrieved from https:\/\/openreview.net\/forum?id=SJU4ayYgl"},{"key":"e_1_3_1_20_2","unstructured":"T. N. Kipf and M. Welling. 2016. Variational graph auto-encoders. arXiv:1611.07308. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.1611.07308"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2879624"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11771"},{"key":"e_1_3_1_24_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"33","author":"Luo D.","year":"2020","unstructured":"D. Luo, W. Cheng, D. Xu, W. Yu, B. Zong, H. Chen, and X. Zhang. 2020. Parameterized explainer for graph neural network. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33."},{"key":"e_1_3_1_25_2","first-page":"15524","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Miao S.","year":"2022","unstructured":"S. Miao, M. Liu, and P. Li. 2022. Interpretable and generalizable graph learning via stochastic attention mechanism. In Proceedings of the International Conference on Machine Learning. PMLR, 15524\u201315543."},{"key":"e_1_3_1_26_2","first-page":"3111","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems (NeurIPS \u201913)","volume":"2","author":"Mikolov T.","year":"2013","unstructured":"T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the 26th International Conference on Neural Information Processing Systems (NeurIPS \u201913), Vol. 2, 3111\u20133119."},{"key":"e_1_3_1_27_2","unstructured":"N. Papernot and P. McDaniel. 2018. Deep k-nearest neighbors: Towards confident interpretable and robust deep learning. arXiv:1803.04765."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01103"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330935"},{"key":"e_1_3_1_34_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR \u201918)","author":"Veli\u010dkovi\u0107 P.","year":"2018","unstructured":"P. Veli\u010dkovi\u0107, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio. 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations (ICLR \u201918)."},{"key":"e_1_3_1_35_2","first-page":"598","volume-title":"Proceedings of the IEEE International Conference on Data Mining (ICDM \u201919)","author":"Wang D.","year":"2019","unstructured":"D. Wang, J. Lin, P. Cui, Q. Jia, Z. Wang, Y. Fang, Q. Yu, J. Zhou, S. Yang, and Y. Qi. 2019. A semi-supervised graph attentive network for financial fraud detection. In Proceedings of the IEEE International Conference on Data Mining (ICDM \u201919). IEEE, 598\u2013607."},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330836"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"e_1_3_1_38_2","volume-title":"Proceedings of 7th International Conference on Learning Representations (ICLR 2017)","author":"Xu K.","year":"2019","unstructured":"K. Xu, W. Hu, J. Leskovec, and S. Jegelka. 2019. How powerful are graph neural networks? In Proceedings of 7th International Conference on Learning Representations (ICLR 2017). Retrieved from https:\/\/openreview.net\/forum?id=ryGs6iA5Km"},{"key":"e_1_3_1_39_2","first-page":"5453","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xu K.","year":"2018","unstructured":"K. Xu, C. Li, Y. Tian, T. Sonobe, K.-I. Kawarabayashi, and S. Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. In Proceedings of the International Conference on Machine Learning. PMLR, 5453\u20135462."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_1_41_2","first-page":"9244","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Ying Z.","year":"2019","unstructured":"Z. Ying, D. Bourgeois, J. You, M. Zitnik, and J. Leskovec. 2019. GNNExplainer: Generating explanations for graph neural networks. In Proceedings of the Advances in Neural Information Processing Systems, 9244\u20139255."},{"key":"e_1_3_1_42_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"33","author":"You Y.","year":"2020","unstructured":"Y. You, T. Chen, Y. Sui, T. Chen, Z. Wang, and Y. Shen. 2020. Graph contrastive learning with augmentations. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015717"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204236"},{"key":"e_1_3_1_46_2","first-page":"12241","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML \u201921)","author":"Yuan H.","year":"2021","unstructured":"H. Yuan, H. Yu, J. Wang, K. Li, and S. Ji. 2021. On explainability of graph neural networks via subgraph explorations. In Proceedings of the 38th International Conference on Machine Learning (ICML \u201921), 12241\u201312252."},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_3_1_48_2","first-page":"9127","volume-title":"Proceedings of Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022)","author":"Zhang Z.","year":"2021","unstructured":"Z. Zhang, Q. Liu, H. Wang, C. Lu, and C. Lee. 2021. ProtGNN: Towards self-explaining graph neural networks. In Proceedings of Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022), 9127\u20139135."},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411977"},{"key":"e_1_3_1_50_2","unstructured":"Q. Zhu B. Du and P. Yan. 2020. Self-supervised training of graph convolutional networks. arXiv:2006.02380."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689647","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:47Z","timestamp":1750295387000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,14]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2,28]]}},"alternative-id":["10.1145\/3689647"],"URL":"https:\/\/doi.org\/10.1145\/3689647","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":"2023-09-09","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"}}]}}