{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T02:02:01Z","timestamp":1783476121669,"version":"3.55.0"},"reference-count":151,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FT210100097"],"award-info":[{"award-number":["FT210100097"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP240101547"],"award-info":[{"award-number":["DP240101547"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DE260101172"],"award-info":[{"award-number":["DE260101172"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grants Council of Hong Kong CityU","award":["11301224"],"award-info":[{"award-number":["11301224"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62536006"],"award-info":[{"award-number":["62536006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["III-2106758"],"award-info":[{"award-number":["III-2106758"]}]},{"name":"NSF","award":["POSE-2346158"],"award-info":[{"award-number":["POSE-2346158"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tkde.2026.3680353","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:52:24Z","timestamp":1775159544000},"page":"4385-4404","source":"Crossref","is-referenced-by-count":12,"title":["Graph Neural Networks for Graphs With Heterophily: A Survey"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0915-7787","authenticated-orcid":false,"given":"Xin","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computing Technologies, RMIT University, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6897-1054","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mathematics, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4309-5076","authenticated-orcid":false,"given":"Yixin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Southport, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1218-2804","authenticated-orcid":false,"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University, Jinhua, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1262-4174","authenticated-orcid":false,"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7445-9936","authenticated-orcid":false,"given":"Di","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-527X","authenticated-orcid":false,"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Southport, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557108"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3144993"},{"key":"ref3","first-page":"5250","article-title":"Composition-based multi-relational graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Vashishth"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403118"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref6","first-page":"5711","article-title":"Learning disentangled representations for recommendation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref7","first-page":"2713","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref8","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref9","first-page":"2920","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref10","first-page":"9104","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref12","first-page":"7548","article-title":"Graph geometry interaction learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref13","first-page":"8975","article-title":"Towards self-interpretable graph-level anomaly detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0264"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1460"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1140\/epjds\/s13688-016-0068-2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583498"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00165"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512186"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00089"},{"key":"ref21","first-page":"42492","article-title":"Finding the missing-half: Graph complementary learning for homophily-prone and heterophily-prone graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242600"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17332"},{"key":"ref24","first-page":"7793","article-title":"Beyond homophily in graph neural networks: Current limitations and effective designs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16514"},{"key":"ref26","first-page":"20887","article-title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref27","first-page":"20887","article-title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref28","article-title":"Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks","author":"Yan","year":"2021"},{"key":"ref29","first-page":"4751","article-title":"Diverse message passing for attribute with heterophily","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref30","first-page":"16138","article-title":"Adaptive universal generalized PageRank graph neural network","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chien"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25573"},{"issue":"2","key":"ref32","first-page":"10","article-title":"Heterophily and graph neural networks: Past, present and future","volume":"47","author":"Zhu","year":"2023","journal-title":"IEEE Data Eng. Bull."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-025-41059-z"},{"key":"ref34","article-title":"The heterophilic graph learning handbook: Benchmarks, models, theoretical analysis, applications and challenges","author":"Luan","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2026.3680353"},{"key":"ref36","volume-title":"Extremal Graph Theory","author":"Bollob\u00e1s","year":"2004"},{"key":"ref37","first-page":"10247","article-title":"Geom-GCN: Geometric graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pei"},{"key":"ref38","first-page":"523","article-title":"Characterizing graph datasets for node classification: Homophily-heterophily dichotomy and beyond","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Platonov"},{"key":"ref39","first-page":"1","article-title":"Revisiting graph homophily measures","volume-title":"Proc. Learn. Graphs Conf.","author":"Mironov"},{"key":"ref40","first-page":"18738","article-title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Platonov"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482487"},{"key":"ref43","first-page":"35954","article-title":"Ordered GNN: Ordering message passing to deal with heterophily and over-smoothing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref44","first-page":"4694","article-title":"EvenNet: Ignoring odd-hop neighbors improves robustness of graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref45","first-page":"10654","article-title":"Universal graph convolutional networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441735"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3257325"},{"key":"ref48","article-title":"MPformer: Advancing graph modeling through heterophily relationship-based position encoding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00188"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889874"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761256"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20340"},{"key":"ref53","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":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1346"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583453"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00761"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/278"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761090"},{"key":"ref59","first-page":"1362","article-title":"Revisiting heterophily for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Luan"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512201"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512185"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512100"},{"key":"ref63","first-page":"3648","article-title":"Optimization-induced graph implicit nonlinear diffusion","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1971"},{"key":"ref65","first-page":"1","article-title":"Leave graphs alone: Addressing over-squashing without rewiring","volume-title":"Proc. Learn. Graphs Conf.","author":"Tortorella"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3179306"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3230417"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3186016"},{"key":"ref69","first-page":"17375","article-title":"GOAT: A global transformer on large-scale graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kong"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583335"},{"key":"ref71","first-page":"70162","article-title":"From trainable negative depth to edge heterophily in graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yan"},{"key":"ref72","first-page":"10909","article-title":"Predicting global label relationship matrix for graph neural networks under heterophily","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29514"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29246"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01261-8"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2966"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3370918"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3441766"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3412149"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889462"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/722"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3775057"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736936"},{"key":"ref84","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref85","article-title":"From local to global: Spectral-inspired graph neural networks","volume-title":"Proc. NeurIPS 2022 Workshop: New Frontiers Graph Learn.","author":"Huang"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094813"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref88","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3161453"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3282049"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1967.21.343"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3134200"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20864"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747635"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3267902"},{"key":"ref96","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467373"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/293"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20319"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20765"},{"key":"ref101","first-page":"18960","article-title":"Integrating co-training with edge discrimination to enhance graph neural networks under heterophily","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Siqi"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3118815"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/234"},{"key":"ref104","first-page":"26342","article-title":"Is homophily a necessity for graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2006.72"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1002\/asi.21171"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3327266"},{"key":"ref108","first-page":"6694","article-title":"GReTo: Remedying dynamic graph topology-task discordance via target homophily","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.34022"},{"key":"ref110","first-page":"16983","article-title":"Equivariant hypergraph diffusion neural operators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref111","first-page":"2079","article-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3397536.3422208"},{"key":"ref113","article-title":"Higher-order homophily is combinatorially impossible","author":"Veldt","year":"2022"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.socnet.2005.11.003"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380152"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abh1303"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737421"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3540063"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3201243"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/669"},{"key":"ref121","first-page":"9263","article-title":"GNNGUARD: Defending graph neural networks against adversarial attacks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref122","first-page":"1","article-title":"GARNET: Reduced-rank topology learning for robust and scalable graph neural networks","volume-title":"Proc. Learn. Graphs Conf.","author":"Deng"},{"key":"ref123","first-page":"15404","article-title":"Understanding and improving graph injection attack by promoting unnoticeability","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539418"},{"key":"ref125","first-page":"40078","article-title":"Multi-track message passing: Tackling oversmoothing and oversquashing in graph learning via preventing heterophily mixing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pei"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570377"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512195"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33356"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583268"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3188662"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539483"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3319468"},{"key":"ref133","first-page":"12775","article-title":"Contrastive learning meets homophily: Two birds with one stone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"He"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3146270"},{"key":"ref135","first-page":"9244","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref136","first-page":"19620","article-title":"Parameterized explainer for graph neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-01974-x"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref139","first-page":"1979","article-title":"GraphSAINT: Graph sampling based inductive learning method","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng"},{"key":"ref140","first-page":"620","article-title":"Decoupled self-supervised learning for graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref141","article-title":"Link prediction on heterophilic graphs via disentangled representation learning","author":"Zhou","year":"2022"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3400402"},{"key":"ref143","first-page":"64806","article-title":"Multi-domain graph foundation models: Robust knowledge transfer via topology alignment","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref144","first-page":"63169","article-title":"Cooperation of experts: Fusing heterogeneous information with large margin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1080\/07350015.2021.1930013"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557324"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111187"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0402"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3224734"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW60847.2023.00143"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583373"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/69\/11538062\/11471063-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11538062\/11471063.pdf?arnumber=11471063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:09Z","timestamp":1780948449000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":151,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3680353","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}