{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:59:32Z","timestamp":1772906372414,"version":"3.50.1"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Research and Development Program of Zhejiang","award":["2022C01018"],"award-info":[{"award-number":["2022C01018"]}]},{"name":"China Post-Doctoral Science Foundation","award":["2024M762912"],"award-info":[{"award-number":["2024M762912"]}]},{"name":"Post-Doctoral Science Preferential Funding of Zhejiang Province of China","award":["ZJ2024060"],"award-info":[{"award-number":["ZJ2024060"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2001"],"award-info":[{"award-number":["U21B2001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Technology Research and Development Program of Hangzhou","award":["2024SZD1A23"],"award-info":[{"award-number":["2024SZD1A23"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2025.3528738","type":"journal-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:49:27Z","timestamp":1736884167000},"page":"2882-2896","source":"Crossref","is-referenced-by-count":5,"title":["Clarify Confused Nodes via Separated Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5062-4183","authenticated-orcid":false,"given":"Jiajun","family":"Zhou","sequence":"first","affiliation":[{"name":"Institute of Cyberspace Security, College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7482-6524","authenticated-orcid":false,"given":"Shengbo","family":"Gong","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5047-7586","authenticated-orcid":false,"given":"Xuanze","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxuan","family":"Xie","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5170-8082","authenticated-orcid":false,"given":"Shanqing","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1042-470X","authenticated-orcid":false,"given":"Qi","family":"Xuan","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3117-2211","authenticated-orcid":false,"given":"Xiaoniu","family":"Yang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Electromagnetic Space Security, Jiaxing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3118815"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3129349"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3066111"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3025588"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3208471"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3384499"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3142260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263079"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3080635"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645693"},{"key":"ref11","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref12","first-page":"1","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref13","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539483"},{"key":"ref15","article-title":"Graph neural networks for graphs with heterophily: A survey","author":"Zheng","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3324937"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449952"},{"key":"ref18","first-page":"37 013","article-title":"Demystifying structural disparity in graph neural networks: Can one size fit all?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mao"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26038"},{"key":"ref20","first-page":"1","article-title":"Adaptive universal generalized pagerank graph neural network","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chien"},{"key":"ref21","first-page":"14 239","article-title":"Bernnet: Learning arbitrary graph spectral filters via bernstein approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He"},{"key":"ref22","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106650"},{"key":"ref24","first-page":"1362","article-title":"Revisiting heterophily for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16514"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20340"},{"key":"ref27","first-page":"1","article-title":"Energy-based out-of-distribution detection for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref28","first-page":"30 277","article-title":"Graphde: A generative framework for debiased learning and out-of-distribution detection on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1108\/00220410810844150"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512201"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00169"},{"key":"ref32","first-page":"1","article-title":"Geom-GCN: Geometric graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pei"},{"key":"ref33","first-page":"1","article-title":"Is homophily a necessity for graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539374"},{"key":"ref36","first-page":"1","article-title":"Graph neural networks exponentially lose expressive power for node classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Oono"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref38","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":"ref39","first-page":"1","article-title":"Break the ceiling: Stronger multi-scale deep graph convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luan"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-019-0069-y"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467373"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.03.057"},{"key":"ref43","first-page":"1","article-title":"2-hop neighbor class similarity (2ncs): A graph structural metric indicative of graph neural network performance","volume-title":"Proc. 3rd Workshop Graphs More Complex Struct. Learn. Reasoning","author":"Cavallo"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3267902"},{"key":"ref45","article-title":"Bag of tricks of semi-supervised classification with graph neural networks","author":"Wang","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583268"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17332"},{"key":"ref48","first-page":"26","article-title":"Label-wise graph convolutional network for heterophilic graphs","volume-title":"Proc. Learn. Graphs Conf.","author":"Dai"},{"key":"ref49","article-title":"Pitfalls of graph neural network evaluation","author":"Shchur","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1119\/1.1937609"},{"key":"ref51","first-page":"13 366","article-title":"Diffusion improves graph learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Klicpera"},{"key":"ref52","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/qss_a_00021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref56","first-page":"1","article-title":"Deep Gaussian embedding of graphs: Unsupervised inductive learning via ranking","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bojchevski"},{"key":"ref57","first-page":"20 887","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":"ref58","first-page":"1","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":"ref59","first-page":"13 242","article-title":"Finding global homophily in graph neural networks when meeting heterophily","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref60","first-page":"1","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gasteiger"},{"key":"ref61","article-title":"Distilling self-knowledge from contrastive links to classify graph nodes without passing messages","author":"Luo","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/math10081262"},{"key":"ref63","first-page":"31 613","article-title":"Exphormer: Sparse transformers for graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shirzad"},{"key":"ref64","first-page":"12 077","article-title":"Graph neural networks with learnable and optimal polynomial bases","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref65","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref66","article-title":"Neural network intelligence","year":"2021"},{"key":"ref67","first-page":"1","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bergstra"},{"key":"ref68","first-page":"1","article-title":"Graphsaint: Graph sampling based inductive learning method","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng"},{"key":"ref69","article-title":"Data augmentation on graphs: A technical survey","author":"Zhou","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10840207.pdf?arnumber=10840207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:38:53Z","timestamp":1741372733000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10840207\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":69,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3528738","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":[[2025,4]]}}}