{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T11:11:54Z","timestamp":1774782714005,"version":"3.50.1"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000009","name":"Foundation for the National Institutes of Health","doi-asserted-by":"publisher","award":["U01CA249245"],"award-info":[{"award-number":["U01CA249245"]}],"id":[{"id":"10.13039\/100000009","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000009","name":"Foundation for the National Institutes of Health","doi-asserted-by":"publisher","award":["1R01HG011035"],"award-info":[{"award-number":["1R01HG011035"]}],"id":[{"id":"10.13039\/100000009","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000009","name":"Foundation for the National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM141519"],"award-info":[{"award-number":["R01GM141519"]}],"id":[{"id":"10.13039\/100000009","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000009","name":"Foundation for the National Institutes of Health","doi-asserted-by":"publisher","award":["1U01AI169298"],"award-info":[{"award-number":["1U01AI169298"]}],"id":[{"id":"10.13039\/100000009","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000009","name":"Foundation for the National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM140012"],"award-info":[{"award-number":["R01GM140012"]}],"id":[{"id":"10.13039\/100000009","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004917","name":"Cancer Prevention and Research Institute of Texas","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004917","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neucom.2026.133373","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T07:36:04Z","timestamp":1773992164000},"page":"133373","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["GNN-EGG: Graph neural network explanations via graph generation"],"prefix":"10.1016","volume":"681","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8552-0846","authenticated-orcid":false,"given":"Art","family":"Taychameekiatchai","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2118-6428","authenticated-orcid":false,"given":"Liwei","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Zhikai","family":"Chi","sequence":"additional","affiliation":[]},{"given":"Yueshuang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Qin","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Guanghua","family":"Xiao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-7193","authenticated-orcid":false,"given":"Xiaowei","family":"Zhan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133373_bib0005","series-title":"2016 IEEE 2nd International Conference on Collaboration and Internet Computing (CIC)","first-page":"329","article-title":"Detecting discrimination in a black-box classifier","author":"Alufaisan","year":"2016"},{"key":"10.1016\/j.neucom.2026.133373_bib0010","series-title":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","first-page":"1988","article-title":"Unsupervised inductive graph-level representation learning via graph-graph proximity","author":"Bai","year":"2019"},{"key":"10.1016\/j.neucom.2026.133373_bib0015","author":"Baldassarre"},{"key":"10.1016\/j.neucom.2026.133373_bib0020","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.patrec.2016.10.001","article-title":"Graph edit distance as a quadratic assignment problem","volume":"87","author":"Bougleux","year":"2017","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2026.133373_bib0025","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1016\/S0167-8655(97)00060-3","article-title":"On a relation between graph edit distance and maximum common subgraph","volume":"18","author":"Bunke","year":"1997","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2026.133373_bib0030","series-title":"2013 IEEE International Conference on Computer Vision","first-page":"25","article-title":"Learning graphs to match","author":"Cho","year":"2013"},{"key":"10.1016\/j.neucom.2026.133373_bib0035","series-title":"Computer Vision \u2013 ECCV 2010","first-page":"492","article-title":"Reweighted random walks for graph matching","author":"Cho","year":"2010"},{"key":"10.1016\/j.neucom.2026.133373_bib0040","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1021\/jm00106a046","article-title":"Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity","volume":"34","author":"Debnath","year":"1991","journal-title":"J. Med. Chem."},{"key":"10.1016\/j.neucom.2026.133373_bib0045","author":"Doshi-Velez"},{"key":"10.1016\/j.neucom.2026.133373_bib0050","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.neucom.2026.133373_bib0055","series-title":"Hard masking for explaining graph neural networks","author":"Funke","year":"2020"},{"key":"10.1016\/j.neucom.2026.133373_bib0060","first-page":"3898","article-title":"Fast and deep graph neural networks","volume":"34","author":"Gallicchio","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133373_bib0065","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s10044-008-0141-y","article-title":"A survey of graph edit distance","volume":"13","author":"Gao","year":"2010","journal-title":"Pattern Anal. Appl."},{"key":"10.1016\/j.neucom.2026.133373_bib0070","author":"Garg"},{"key":"10.1016\/j.neucom.2026.133373_bib0075","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.66.046109","article-title":"Evolutionary reconstruction of networks","volume":"66","author":"Ipsen","year":"2002","journal-title":"Phys. Rev. E"},{"key":"10.1016\/j.neucom.2026.133373_bib0080","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1016\/j.laa.2011.08.019","article-title":"Spectral distances of graphs","volume":"436","author":"Jovanovi\u0107","year":"2012","journal-title":"Linear Algebra Appl."},{"key":"10.1016\/j.neucom.2026.133373_bib0085","series-title":"International Conference on Learning Representations","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.neucom.2026.133373_bib0090","series-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds","article-title":"Understanding attention and generalization in graph neural networks","author":"Knyazev","year":"2019"},{"key":"10.1016\/j.neucom.2026.133373_bib0095","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1158\/1535-7163.MCT-17-0019","article-title":"Tumor-associated macrophages can contribute to antitumor activity through fcr-mediated processing of antibody-drug conjugates","volume":"16","author":"Li","year":"2017","journal-title":"Mol. Cancer Ther."},{"key":"10.1016\/j.neucom.2026.133373_bib0100","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13728","article-title":"Orphicx: a causality-inspired latent variable model for interpreting graph neural networks","author":"Lin","year":"2022"},{"key":"10.1016\/j.neucom.2026.133373_bib0105","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1002\/dc.21519","article-title":"Cytological cell blocks: predictors of squamous cell carcinoma and adenocarcinoma subtypes","volume":"40","author":"Loukeris","year":"2012","journal-title":"Diagn. Cytopathol."},{"key":"10.1016\/j.neucom.2026.133373_bib0110","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Parameterized explainer for graph neural network","author":"Luo","year":"2020"},{"key":"10.1016\/j.neucom.2026.133373_bib0115","series-title":"International Conference on Learning Representations","article-title":"The concrete distribution: a continuous relaxation of discrete random variables","author":"Maddison","year":"2017"},{"key":"10.1016\/j.neucom.2026.133373_bib0120","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10764","article-title":"Explainability methods for graph convolutional neural networks","author":"Pope","year":"2019"},{"key":"10.1016\/j.neucom.2026.133373_bib0125","series-title":"Procedia Computer Science","first-page":"197","article-title":"Frequent subgraph mining algorithms \u2013 a survey","author":"Ramraj","year":"2015"},{"key":"10.1016\/j.neucom.2026.133373_bib0130","series-title":"International Conference on Learning Representations","article-title":"Interpreting graph neural networks for NLP with differentiable edge masking","author":"Schlichtkrull","year":"2021"},{"key":"10.1016\/j.neucom.2026.133373_bib0135","doi-asserted-by":"crossref","first-page":"7581","DOI":"10.1109\/TPAMI.2021.3115452","article-title":"Higher-order explanations of graph neural networks via relevant walks","volume":"44","author":"Schnake","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133373_bib0140","series-title":"Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Process- Ing (TextGraphs-13)","first-page":"58","article-title":"Layerwise relevance visualization in convolutional text graph classifiers","author":"Schwarzenberg","year":"2019"},{"key":"10.1016\/j.neucom.2026.133373_bib0145","first-page":"2539","article-title":"Weisfeiler-Lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133373_bib0150","series-title":"Companion Proceedings of the ACM Web Conference 2024","first-page":"887","article-title":"Is cosine-similarity of embeddings really about similarity?","author":"Steck","year":"2024"},{"key":"10.1016\/j.neucom.2026.133373_bib0155","doi-asserted-by":"crossref","first-page":"7693","DOI":"10.1109\/TKDE.2021.3130903","article-title":"Adversarial attack and defense on graph data: a survey","volume":"35","author":"Sun","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.133373_bib0160","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"10.1016\/j.neucom.2026.133373_bib0165","first-page":"1","article-title":"Pygmtools: a Python graph matching toolkit","volume":"25","author":"Wang","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133373_bib0170","first-page":"5261","article-title":"Neural graph matching network: learning lawler\u2019s quadratic assignment problem with extension to hypergraph and multiple-graph matching","volume":"44","author":"Wang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133373_bib0175","doi-asserted-by":"crossref","first-page":"2056","DOI":"10.1158\/0008-5472.CAN-19-1629","article-title":"Computational staining of pathology images to study the tumor microenvironment in lung cancer","volume":"80","author":"Wang","year":"2020","journal-title":"Cancer Res."},{"key":"10.1016\/j.neucom.2026.133373_bib0180","doi-asserted-by":"crossref","first-page":"7872","DOI":"10.1038\/s41467-023-43172-8","article-title":"Deep learning of cell spatial organizations identifies clinically relevant insights in tissue images","volume":"14","author":"Wang","year":"2023","journal-title":"Nat. Commun."},{"key":"10.1016\/j.neucom.2026.133373_bib0185","series-title":"The Eleventh International Conference on Learning Representations","article-title":"GNNInterpreter: a probabilistic generative model-level explanation for graph neural networks","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133373_bib0190","series-title":"Causal screening to interpret graph neural networks","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133373_bib0195","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"Towards multi-grained explainability for graph neural networks","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133373_bib0200","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.inffus.2022.11.013","article-title":"Beyond explaining: opportunities and challenges of XAI-based model improvement","volume":"92","author":"Weber","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133373_bib0205","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1561\/2200000096","article-title":"Graph neural networks for natural language processing: a survey","volume":"16","author":"Wu","year":"2023","journal-title":"Found. Trends Mach. Learn."},{"key":"10.1016\/j.neucom.2026.133373_bib0210","author":"Xu"},{"key":"10.1016\/j.neucom.2026.133373_bib0215","first-page":"441","article-title":"Image key-point matching using graph neural networks","author":"Xu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133373_bib0220","series-title":"Proceedings of the 2002 IEEE International Conference on Data Mining (ICDM)","first-page":"721","article-title":"gSpan: graph-based substructure pattern mining","author":"Yan","year":"2002"},{"key":"10.1016\/j.neucom.2026.133373_bib0225","series-title":"Advances in Neural Information Processing Systems","article-title":"GNNexplainer: generating explanations for graph neural networks","author":"Ying","year":"2019"},{"key":"10.1016\/j.neucom.2026.133373_bib0230","series-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","first-page":"430","article-title":"XGNN: towards model-level explanations of graph neural networks","author":"Yuan","year":"2020"},{"key":"10.1016\/j.neucom.2026.133373_bib0235","first-page":"5782","article-title":"Explainability in graph neural networks: a taxonomic survey","volume":"45","author":"Yuan","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133373_bib0240","author":"Yuan"},{"key":"10.1016\/j.neucom.2026.133373_bib0245","first-page":"4960","article-title":"Improving attention mechanism in graph neural networks via cardinality preservation","volume":"10","author":"Zhang","year":"2020","journal-title":"Appl. Sci."},{"key":"10.1016\/j.neucom.2026.133373_bib0250","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1016\/j.soc.2016.02.003","article-title":"Classification and pathology of lung cancer","volume":"25","author":"Zheng","year":"2016","journal-title":"Surg. Oncol. Clin. N. Am."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226007708?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226007708?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T07:02:40Z","timestamp":1774767760000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226007708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":50,"alternative-id":["S0925231226007708"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133373","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GNN-EGG: Graph neural network explanations via graph generation","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133373","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133373"}}