{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:41:45Z","timestamp":1770932505554,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Center for Applied Research in Artificial Intelligence (CARAI) grant"},{"name":"Defense Acquisition Program Administration (DAPA) and Agency for Defense Development","award":["UD230017TD"],"award-info":[{"award-number":["UD230017TD"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3624415","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:39Z","timestamp":1761153939000},"page":"199531-199545","source":"Crossref","is-referenced-by-count":0,"title":["A Mutual Information-Based Framework for Enhancing Graph Neural Networks on Heterophily"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3244-6807","authenticated-orcid":false,"given":"Gahee","family":"Kim","sequence":"first","affiliation":[{"name":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0263-5589","authenticated-orcid":false,"given":"Seongjin","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Pohang University of Science and Technology (POSTECH), Pohang, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6675-5113","authenticated-orcid":false,"given":"Se-Young","family":"Yun","sequence":"additional","affiliation":[{"name":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"ref2","first-page":"6410","article-title":"Graph convolutional policy network for goal-directed molecular graph generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref3","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Duvenaud"},{"key":"ref4","first-page":"6530","article-title":"Protein interface prediction using graph convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Fout"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1198\/016214502388618906"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557109"},{"key":"ref7","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018","journal-title":"arXiv:1810.00826"},{"key":"ref8","article-title":"Inductive matrix completion based on graph neural networks","author":"Zhang","year":"2019","journal-title":"arXiv:1904.12058"},{"key":"ref9","article-title":"Pitfalls of graph neural network evaluation","author":"Shchur","year":"2018","journal-title":"arXiv:1811.05868"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref11","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref12","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref14","article-title":"Graph neural networks for link prediction with subgraph sketching","author":"Paul Chamberlain","year":"2022","journal-title":"arXiv:2209.15486"},{"key":"ref15","first-page":"7793","article-title":"Beyond homophily in graph neural networks: Current limitations and effective designs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242600"},{"key":"ref17","article-title":"Geom-GCN: Geometric graph convolutional networks","author":"Pei","year":"2020","journal-title":"arXiv:2002.05287"},{"key":"ref18","first-page":"13242","article-title":"Finding global homophily in graph neural networks when meeting heterophily","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref19","first-page":"10654","article-title":"Universal graph convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Jin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467373"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3134200"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20864"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20319"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20340"},{"key":"ref26","article-title":"Characterizing graph datasets for node classification: Homophily-heterophily dichotomy and beyond","author":"Platonov","year":"2022","journal-title":"arXiv:2209.06177"},{"key":"ref27","article-title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","author":"Platonov","year":"2023","journal-title":"arXiv:2302.11640"},{"key":"ref28","article-title":"Node mutual information: Enhancing graph neural networks for heterophily","volume-title":"Proc. NeurIPS Workshop, New Frontiers Graph Learn.","author":"Choi"},{"key":"ref29","first-page":"20887","article-title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3371592"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3370918"},{"key":"ref32","article-title":"How universal polynomial bases enhance spectral graph neural networks: Heterophily, over-smoothing, and over-squashing","author":"Huang","year":"2024","journal-title":"arXiv:2405.12474"},{"key":"ref33","article-title":"Slog: An inductive spectral graph neural network beyond polynomial filter","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref34","article-title":"Flexible diffusion scopes with parameterized Laplacian for heterophilic graph learning","author":"Lu","year":"2024","journal-title":"arXiv:2409.09888"},{"key":"ref35","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Hjelm","year":"2018","journal-title":"arXiv:1808.06670"},{"key":"ref36","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belghazi"},{"key":"ref37","article-title":"Deep graph infomax","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"arXiv:1809.10341"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380112"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533715"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/srep44981"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524711"},{"key":"ref42","first-page":"21","article-title":"MixHop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abu-El-Haija"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.09375"},{"key":"ref46","article-title":"Predict then propagate: Graph neural networks meet personalized PageRank","author":"Gasteiger","year":"2018","journal-title":"arXiv:1810.05997"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17332"},{"key":"ref48","article-title":"Adaptive universal generalized PageRank graph neural network","author":"Chien","year":"2020","journal-title":"arXiv:2006.07988"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512201"},{"key":"ref50","article-title":"Edge directionality improves learning on heterophilic graphs","author":"Rossi","year":"2023","journal-title":"arXiv:2305.10498"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511813658"},{"key":"ref52","volume-title":"Probability: A Graduate Course","author":"Gut","year":"2006"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11214418.pdf?arnumber=11214418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:00:48Z","timestamp":1770930048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11214418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3624415","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}