{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T08:10:38Z","timestamp":1780647038022,"version":"3.54.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["IIS-1707548"],"award-info":[{"award-number":["IIS-1707548"]}]},{"name":"NSF","award":["CBET-1638320"],"award-info":[{"award-number":["CBET-1638320"]}]},{"name":"NSF","award":["IIS-2331908"],"award-info":[{"award-number":["IIS-2331908"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tpami.2024.3362584","type":"journal-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T19:00:50Z","timestamp":1707246050000},"page":"5245-5259","source":"Crossref","is-referenced-by-count":19,"title":["Towards Inductive and Efficient Explanations for Graph Neural Networks"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4192-0826","authenticated-orcid":false,"given":"Dongsheng","family":"Luo","sequence":"first","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4504-7809","authenticated-orcid":false,"given":"Tianxiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, State College, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5456-626X","authenticated-orcid":false,"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[{"name":"NEC Lab America, Inc., San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1456-9658","authenticated-orcid":false,"given":"Dongkuan","family":"Xu","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3561-4304","authenticated-orcid":false,"given":"Feng","family":"Han","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2480-448X","authenticated-orcid":false,"given":"Wenchao","family":"Yu","sequence":"additional","affiliation":[{"name":"NEC Lab America, Inc., San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-3135","authenticated-orcid":false,"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, State College, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1318-6583","authenticated-orcid":false,"given":"Haifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"NEC Lab America, Inc., San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0940-6595","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, State College, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Concrete autoencoders for differentiable feature selection and reconstruction","author":"Abid","year":"2019"},{"key":"ref2","first-page":"13378","article-title":"On differentially private graph sparsification and applications","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Arora"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti1007"},{"key":"ref4","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna","year":"2013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788613"},{"key":"ref6","first-page":"883","article-title":"Learning to explain: An information-theoretic perspective on model interpretation","author":"Chen","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0000(89)90044-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3218745"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_36"},{"key":"ref10","first-page":"6967","article-title":"Real time image saliency for black box classifiers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dabkowski"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"ref12","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Defferrard"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5486\/PMD.1959.6.3-4.12"},{"issue":"3","key":"ref14","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"Erhan","year":"2019","journal-title":"Univ. Montreal"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177706098"},{"key":"ref17","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2180-11.2011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref20","first-page":"2434","article-title":"Graphite: Iterative generative modeling of graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Grover"},{"key":"ref21","first-page":"4514","article-title":"Explaining deep learning models\u2013a Bayesian non-parametric approach","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243792"},{"key":"ref23","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.116853"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/17.1.107"},{"key":"ref26","article-title":"A unifying framework for spectrum-preserving graph sparsification and coarsening","author":"Hermsdorff","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1198\/016214502388618906"},{"issue":"2","key":"ref28","article-title":"[Re] parameterized explainer for graph neural network","volume-title":"ReScience C","volume":"7","author":"Holdijk"},{"key":"ref29","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang"},{"key":"ref30","article-title":"Variational graph auto-encoders","author":"Kipf","year":"2016"},{"key":"ref31","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref32","first-page":"31","article-title":"Recognizing cuneiform signs using graph based methods","volume-title":"Proc. Int. Workshop Cost-Sensitive Learn.","author":"Kriege"},{"key":"ref33","article-title":"Interpretable & explorable approximations of black box models","author":"Lakkaraju","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1081870.1081893"},{"key":"ref35","article-title":"Understanding neural networks through representation erasure","author":"Li","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11691"},{"key":"ref37","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"ref38","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441734"},{"key":"ref40","first-page":"4212","article-title":"Disentangled graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref41","first-page":"3276","article-title":"A flexible generative framework for graph-based semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref42","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maddison"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198805090.001.0001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186113"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89689-0_33"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref48","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shrikumar"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"ref50","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1021\/ci034143r"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.05.041"},{"key":"ref53","article-title":"Graph attention networks,","author":"Veli\u010dkovi\u0107","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref54","article-title":"Uncovering hierarchical structure in social networks using isospectral reductions","author":"Wang","year":"2017"},{"key":"ref55","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00256"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref58","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref59","first-page":"5694","article-title":"GraphRNN: Generating realistic graphs with deep auto-regressive models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3204236"},{"key":"ref62","article-title":"On explainability of graph neural networks via subgraph explorations","author":"Yuan","year":"2021"},{"key":"ref63","first-page":"5165","article-title":"Link prediction based on graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3616542"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570421"},{"key":"ref66","first-page":"11458","article-title":"Robust graph representation learning via neural sparsification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref67","article-title":"Deep graph structure learning for robust representations: A survey","author":"Zhu","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10582780\/10423141-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10582780\/10423141.pdf?arnumber=10423141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T08:26:02Z","timestamp":1719995162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10423141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":67,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3362584","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}