{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T02:16:53Z","timestamp":1777861013942,"version":"3.51.4"},"reference-count":61,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T00:00:00Z","timestamp":1775433600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T00:00:00Z","timestamp":1775433600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Graph Neural Networks (GNNs) are currently used in many real\u2010world applications. With this notable spread, the development of sophisticated techniques for explaining their decisions becomes highly necessary. Although many works have been proposed with the aim of explaining their predictions, most of them generate explanations as subgraphs. In this paper, we argue that relying only on explanatory subgraphs is not sufficient. In this regard, we propose CausGNN: a causal explanation framework based on the structural model of causality. By adapting the definition of actual cause, our framework provides comprehensive explanations that incorporate both nodes features and edges in a complementary manner. Furthermore, as the need for robust explanations grows, we address this issue and show that the explanations provided by CausGNN are very robust to perturbations. Finally, CausGNN does not intend to compete with existing explanation frameworks for GNNs, but rather acts as a complementary tool.<\/jats:p>","DOI":"10.1111\/exsy.70252","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T23:45:50Z","timestamp":1775519150000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>CausGNN<\/scp>\n                    : A Causal\u2010Based Explanation Framework for Graph Neural Networks"],"prefix":"10.1111","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0339-1903","authenticated-orcid":false,"given":"Hichem","family":"Debbi","sequence":"first","affiliation":[{"name":"Department of Computer Science, Laboratory of Informatics and Its Applications of M'sila (LIAM) University of M'sila  M'sila Algeria"}]}],"member":"311","published-online":{"date-parts":[[2026,4,6]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467154"},{"key":"e_1_2_11_3_1","unstructured":"Amara K. R.Ying Z.Zhang et\u00a0al.2022.\u201cGraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks.\u201darXiv Preprint arXiv:220609677."},{"key":"e_1_2_11_4_1","first-page":"387","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"Biggio B.","year":"2013"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5731"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645419"},{"issue":"144","key":"e_1_2_11_7_1","article-title":"Evaluating Explainability for Graph Neural Networks","volume":"10","author":"Chirag A.","year":"2023","journal-title":"Nature Scientific Data"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020579"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1391"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1352582.1352588"},{"key":"e_1_2_11_11_1","first-page":"6970","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems NIPS'17","author":"Dabkowski P.","year":"2017"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86520-7_39"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510200"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00056"},{"key":"e_1_2_11_15_1","first-page":"2083","volume-title":"Proceedings of the 36th International Conference on Machine Learning, Vol. 97 of Proceedings of Machine Learning Research","author":"Gao H.","year":"2019"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219947"},{"key":"e_1_2_11_17_1","unstructured":"Goodfellow I. J. J.Shlens andC.Szegedy.2015.\u201cExplaining and Harnessing Adversarial Examples.\u201dhttps:\/\/arxiv.org\/abs\/1412.6572."},{"key":"e_1_2_11_18_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gosch L.","year":"2023"},{"key":"e_1_2_11_19_1","first-page":"194","volume-title":"Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence UAI'01","author":"Halpern J. Y.","year":"2001"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3187455"},{"key":"e_1_2_11_21_1","unstructured":"Jiang W. H.Liu andH.Xiong.2024.\u201cWhen Graph Neural Network Meets Causality: Opportunities Methodologies and an Outlook.\u201dhttps:\/\/arxiv.org\/abs\/2312.12477."},{"key":"e_1_2_11_22_1","unstructured":"Kelly D. A. andH.Chockler.2025.\u201cCausal Identification of Sufficient Contrastive and Complete Feature Sets in Image Classification.\u201dhttps:\/\/arxiv.org\/abs\/2507.23497."},{"key":"e_1_2_11_23_1","volume-title":"Semi\u2010Supervised Classification With Graph Convolutional Networks","author":"Kipf T. N.","year":"2017"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698108"},{"key":"e_1_2_11_25_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning ICML 24","author":"Li J.","year":"2024"},{"key":"e_1_2_11_26_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Li J.","year":"2025"},{"key":"e_1_2_11_27_1","volume-title":"International Conference on Machine Learning","author":"Lin W.","year":"2021"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01336"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403076"},{"key":"e_1_2_11_30_1","doi-asserted-by":"crossref","unstructured":"Liu Y. C.Chen Y.Liu X.Zhang andS.Xie.2021.\u201cMulti\u2010Objective Explanations of GNN Predictions.\u201dhttps:\/\/arxiv.org\/abs\/2111.14651.","DOI":"10.1109\/ICDM51629.2021.00052"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696444"},{"key":"e_1_2_11_32_1","first-page":"19620","article-title":"Parameterized Explainer for Graph Neural Network","volume":"33","author":"Luo D.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3546577"},{"key":"e_1_2_11_34_1","doi-asserted-by":"crossref","unstructured":"Numeroso D. andD.Bacciu.2021.\u201cMEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks.\u201dhttps:\/\/arxiv.org\/abs\/2104.08060.","DOI":"10.1109\/IJCNN52387.2021.9534266"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01103"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30149"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618105"},{"key":"e_1_2_11_38_1","first-page":"1135","article-title":"Why Should I Trust You?: Explaining the Predictions of Any Classifier","author":"Ribeiro M. T.","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbz042"},{"key":"e_1_2_11_42_1","unstructured":"Szegedy C. W.Zaremba I.Sutskever et\u00a0al.2014.\u201cIntriguing Properties of Neural Networks.\u201dhttps:\/\/arxiv.org\/abs\/1312.6199."},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511948"},{"key":"e_1_2_11_44_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems NIPS'21","author":"Triantafyllou S.","year":"2021"},{"key":"e_1_2_11_45_1","volume-title":"Graph Attention Networks","author":"Velickovic P.","year":"2018"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3209435"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10021051"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC05259D"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.156"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/669"},{"key":"e_1_2_11_51_1","first-page":"9240","article-title":"GNNExplainer: Generating Explanations for Graph Neural Networks","volume":"32","author":"Ying R.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_52_1","first-page":"6412","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems NIPS'18","author":"You J.","year":"2018"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015717"},{"key":"e_1_2_11_54_1","volume-title":"Structpool: Structured Graph Pooling via Conditional Random Fields","author":"Yuan H.","year":"2020"},{"issue":"5","key":"e_1_2_11_55_1","first-page":"5782","article-title":"Explainability in Graph Neural Networks: A Taxonomic Survey","volume":"45","author":"Yuan H.","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_11_56_1","first-page":"12241","volume-title":"On Explainability of Graph Neural Networks via Subgraph Explorations","author":"Yuan H.","year":"2021"},{"key":"e_1_2_11_57_1","doi-asserted-by":"crossref","unstructured":"Zhang M. Z.Cui M.Neumann andY.Chen.2018.\u201cAn End\u2010To\u2010End Deep Learning Architecture for Graph Classification. AAAI'18\/IAAI'18\/EAAI'18.\u201d","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462562"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty294"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.012"},{"key":"e_1_2_11_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220078"},{"key":"e_1_2_11_62_1","doi-asserted-by":"crossref","unstructured":"Z\u00fcgner D. andS.G\u00fcnnemann.2019.\u201cAdversarial Attacks on Graph Neural Networks via Meta Learning. In: International Conference on Learning Representations.\u201dhttps:\/\/openreview.net\/forum?id=Bylnx209YX.","DOI":"10.24963\/ijcai.2019\/872"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70252","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70252","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T02:41:54Z","timestamp":1777516914000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70252"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,6]]},"references-count":61,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1111\/exsy.70252"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70252","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,6]]},"assertion":[{"value":"2025-04-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70252"}}