{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:53:57Z","timestamp":1757310837113,"version":"3.41.0"},"reference-count":34,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"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":["SIGMOD Rec."],"published-print":{"date-parts":[[2024,11,8]]},"abstract":"<jats:p>GOAL: Graph Neural Networks (GNNs) are being increasingly adopted in various real-world applications, including drug and material discovery [16, 17, 27], recommendation engines [29], congestion modeling on road networks [5], and weather forecasting [11]. However, similar to other deeplearning models, GNNs are considered black boxes due to their limited capacity to provide explanations for their predictions. This lack of interpretability poses a significant barrier to their adoption in critical domains such as healthcare, finance, and law enforcement, where transparency and trustworthiness are essential for decision-making processes. In these pivotal domains, understanding the rationale behind model predictions is crucial not only for compliance with interpretability requirements but also for identifying potential vulnerabilities and gaining insights to refine the model further. How do we make GNNs interpretable? This is a central motivating question driving my research pursuits.<\/jats:p>","DOI":"10.1145\/3703922.3703930","type":"journal-article","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T23:37:24Z","timestamp":1731109044000},"page":"32-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["The Road to Explainable Graph Neural Networks"],"prefix":"10.1145","volume":"53","author":[{"given":"Sayan","family":"Ranu","sequence":"first","affiliation":[{"name":"Yardi School of AI (Joint Appointment), IIT Delhi"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"KDD, page 2495--2504","author":"Abrate C.","year":"2021","unstructured":"C. Abrate and F. Bonchi. Counterfactual graphs for explainable classification of brain networks. In KDD, page 2495--2504, 2021."},{"key":"e_1_2_1_2_1","volume-title":"KDD","author":"Abrate C.","year":"2021","unstructured":"C. Abrate and F. Bonchi. Counterfactual graphs for explainable classification of brain networks. In KDD, 2021."},{"key":"e_1_2_1_3_1","volume-title":"Advances in Neural Information Processing Systems","author":"Bajaj M.","year":"2021","unstructured":"M. Bajaj, L. Chu, Z. Y. Xue, J. Pei, L. Wang, P. C.-H. Lam, and Y. Zhang. Robust counterfactual explanations on graph neural networks. In A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan, editors, Advances in Neural Information Processing Systems, 2021."},{"key":"e_1_2_1_4_1","volume-title":"Robust counterfactual explanations on graph neural networks. arXiv preprint arXiv:2107.04086","author":"Bajaj M.","year":"2021","unstructured":"M. Bajaj, L. Chu, Z. Y. Xue, J. Pei, L. Wang, P. C.-H. Lam, and Y. Zhang. Robust counterfactual explanations on graph neural networks. arXiv preprint arXiv:2107.04086, 2021."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481916"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380201"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3187455"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570376"},{"key":"e_1_2_1_9_1","volume-title":"Robust ante-hoc graph explainer using bilevel optimization","author":"Kosan M.","year":"2023","unstructured":"M. Kosan, A. Silva, and A. Singh. Robust ante-hoc graph explainer using bilevel optimization, 2023."},{"key":"e_1_2_1_10_1","volume-title":"Gnnx-bench: Unravelling the utility of perturbation-based gnn explainers through in-depth benchmarking","author":"Kosan M.","year":"2023","unstructured":"M. Kosan, S. Verma, B. Armgaan, K. Pahwa, A. Singh, S. Medya, and S. Ranu. Gnnx-bench: Unravelling the utility of perturbation-based gnn explainers through in-depth benchmarking, 2023."},{"key":"e_1_2_1_11_1","volume-title":"Learning skillful medium-range global weather forecasting. Science, 0(0):eadi2336","author":"Lam R.","year":"2023","unstructured":"R. Lam, A. Sanchez-Gonzalez, M. Willson, P. Wirnsberger, M. Fortunato, F. Alet, S. Ravuri, T. Ewalds, Z. Eaton-Rosen, W. Hu, A. Merose, S. Hoyer, G. Holland, O. Vinyals, J. Stott, A. Pritzel, S. Mohamed, and P. Battaglia. Learning skillful medium-range global weather forecasting. Science, 0(0):eadi2336, 2023."},{"key":"e_1_2_1_12_1","first-page":"6666","volume-title":"International Conference on Machine Learning","author":"Lin W.","year":"2021","unstructured":"W. Lin, H. Lan, and B. Li. Generative causal explanations for graph neural networks. In International Conference on Machine Learning, pages 6666--6679. PMLR, 2021."},{"key":"e_1_2_1_13_1","first-page":"4499","volume-title":"AISTATS","author":"Lucic A.","year":"2022","unstructured":"A. Lucic, M. A. Ter Hoeve, G. Tolomei, M. De Rijke, and F. Silvestri. Cf-gnnexplainer: Counterfactual explanations for graph neural networks. In AISTATS, pages 4499--4511, 2022."},{"key":"e_1_2_1_14_1","volume-title":"Parameterized explainer for graph neural network. Advances in neural information processing systems, 33:19620--19631","author":"Luo D.","year":"2020","unstructured":"D. Luo, W. Cheng, D. Xu, W. Yu, B. Zong, H. Chen, and X. Zhang. Parameterized explainer for graph neural network. Advances in neural information processing systems, 33:19620--19631, 2020."},{"key":"e_1_2_1_15_1","volume-title":"Parameterized explainer for graph neural network. arXiv preprint arXiv:2011.04573","author":"Luo D.","year":"2020","unstructured":"D. Luo, W. Cheng, D. Xu, W. Yu, B. Zong, H. Chen, and X. Zhang. Parameterized explainer for graph neural network. arXiv preprint arXiv:2011.04573, 2020."},{"key":"e_1_2_1_16_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41586-023-06735-9","article-title":"Scaling deep learning for materials discovery","volume":"624","author":"Merchant A.","year":"2023","unstructured":"A. Merchant, S. Batzner, S. Schoenholz, M. Aykol, G. Cheon, and E. Cubuk. Scaling deep learning for materials discovery. Nature, 624:1--6, 11 2023.","journal-title":"Nature"},{"key":"e_1_2_1_17_1","first-page":"35","article-title":"Recipe for a General, Powerful","author":"Ramp\u00e1'ek L.","year":"2022","unstructured":"L. Ramp\u00e1'ek, M. Galkin, V. P. Dwivedi, A. T. Luu, G. Wolf, and D. Beaini. Recipe for a General, Powerful, Scalable Graph Transformer. Advances in Neural Information Processing Systems, 35, 2022.","journal-title":"Scalable Graph Transformer. Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_18_1","first-page":"3839","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS'18","author":"Scaman K.","year":"2018","unstructured":"K. Scaman and A. Virmaux. Lipschitz regularity of deep neural networks: Analysis and efficient estimation. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS'18, page 3839--3848, 2018."},{"key":"e_1_2_1_19_1","volume-title":"NeurIPS 2021","author":"Shan C.","year":"2021","unstructured":"C. Shan, Y. Shen, Y. Zhang, X. Li, and D. Li. Reinforcement learning enhanced explainer for graph neural networks. In NeurIPS 2021, December 2021."},{"key":"e_1_2_1_20_1","volume-title":"International Conference on Learning Representations","author":"Szegedy C.","year":"2014","unstructured":"C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus. Intriguing properties of neural networks. In International Conference on Learning Representations, 2014."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511948"},{"key":"e_1_2_1_22_1","volume-title":"WebConf","author":"Tan J.","year":"2022","unstructured":"J. Tan, S. Geng, Z. Fu, Y. Ge, S. Xu, Y. Li, and Y. Zhang. Learning and evaluating graph neural network explanations based on counterfactual and factual reasoning. In WebConf, 2022."},{"key":"e_1_2_1_23_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Vignac C.","year":"2023","unstructured":"C. Vignac, I. Krawczuk, A. Siraudin, B. Wang, V. Cevher, and P. Frossard. Digress: Discrete denoising diffusion for graph generation. In The Eleventh International Conference on Learning Representations, 2023."},{"key":"e_1_2_1_24_1","volume-title":"Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. Advances in neural information processing systems, 33:12225--12235","author":"Vu M.","year":"2020","unstructured":"M. Vu and M. T. Thai. Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. Advances in neural information processing systems, 33:12225--12235, 2020."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC05259D"},{"key":"e_1_2_1_26_1","unstructured":"H. Xuanyuan P. Barbiero D. Georgiev L. C."},{"key":"e_1_2_1_27_1","volume-title":"Do transformers really perform badly for graph representation? In A","author":"Ying C.","year":"2021","unstructured":"C. Ying, T. Cai, S. Luo, S. Zheng, G. Ke, D. He, Y. Shen, and T.-Y. Liu. Do transformers really perform badly for graph representation? In A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan, editors, Advances in Neural Information Processing Systems, 2021."},{"key":"e_1_2_1_28_1","volume-title":"Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, 32:9240","author":"Ying R.","year":"2019","unstructured":"R. Ying, D. Bourgeois, J. You, M. Zitnik, and J. Leskovec. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, 32:9240, 2019."},{"key":"e_1_2_1_29_1","volume-title":"KDD, page 974--983","author":"Ying R.","year":"2018","unstructured":"R. Ying, R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec. Graph convolutional neural networks for web-scale recommender systems. In KDD, page 974--983, 2018."},{"key":"e_1_2_1_30_1","volume-title":"Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, 32","author":"Ying Z.","year":"2019","unstructured":"Z. Ying, D. Bourgeois, J. You, M. Zitnik, and J. Leskovec. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, 32, 2019."},{"key":"e_1_2_1_31_1","series-title":"Proceedings of Machine Learning Research","first-page":"5694","volume-title":"ICML","author":"You J.","year":"2018","unstructured":"J. You, R. Ying, X. Ren, W. L. Hamilton, and J. Leskovec. Graphrnn: Generating realistic graphs with deep auto-regressive models. In ICML, 2018, volume 80 of Proceedings of Machine Learning Research, pages 5694--5703. PMLR, 2018."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204236"},{"key":"e_1_2_1_34_1","first-page":"12241","volume-title":"ICML","author":"Yuan H.","year":"2021","unstructured":"H. Yuan, H. Yu, J. Wang, K. Li, and S. Ji. On explainability of graph neural networks via subgraph explorations. In ICML, pages 12241--12252. PMLR, 2021. 34"}],"container-title":["ACM SIGMOD Record"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703922.3703930","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703922.3703930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:06Z","timestamp":1750295886000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703922.3703930"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,8]]},"references-count":34,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,11,8]]}},"alternative-id":["10.1145\/3703922.3703930"],"URL":"https:\/\/doi.org\/10.1145\/3703922.3703930","relation":{},"ISSN":["0163-5808"],"issn-type":[{"type":"print","value":"0163-5808"}],"subject":[],"published":{"date-parts":[[2024,11,8]]},"assertion":[{"value":"2024-11-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}