{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:18:31Z","timestamp":1776442711307,"version":"3.51.2"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007567","name":"City University of Hong Kong Project","doi-asserted-by":"publisher","award":["9229031"],"award-info":[{"award-number":["9229031"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372485"],"award-info":[{"award-number":["62372485"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011314"],"award-info":[{"award-number":["2023A1515011314"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010226","name":"Department of Education of Guangdong Province","doi-asserted-by":"publisher","award":["2024ZDZX1001"],"award-info":[{"award-number":["2024ZDZX1001"]}],"id":[{"id":"10.13039\/501100010226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities, Sun Yat-sen University","doi-asserted-by":"publisher","award":["24lgqb018"],"award-info":[{"award-number":["24lgqb018"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tsmc.2025.3548860","type":"journal-article","created":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:43:19Z","timestamp":1742604199000},"page":"3989-4000","source":"Crossref","is-referenced-by-count":3,"title":["What Contributes More to the Robustness of Heterophilic Graph Neural Networks?"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2225-053X","authenticated-orcid":false,"given":"Junyuan","family":"Fang","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, Kowloon, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6477-9669","authenticated-orcid":false,"given":"Han","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5155-8547","authenticated-orcid":false,"given":"Jiajing","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7872-7718","authenticated-orcid":false,"given":"Zibin","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0462-3999","authenticated-orcid":false,"given":"Chi K.","family":"Tse","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, Kowloon, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"493","article-title":"Information network or social network? The structure of the twitter follow graph","volume-title":"Proc. WWW","author":"Myers"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/316194.316229"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2021.3101980"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3130149"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3237933"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2874822"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref10","article-title":"Graph neural network for traffic forecasting: A survey","author":"Jiang","year":"2021","journal-title":"arXiv:2101.11174"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3196506"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2960085"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2917215"},{"key":"ref14","article-title":"Graph neural networks for graphs with heterophily: A survey","author":"Zheng","year":"2022","journal-title":"arXiv:2202.07082"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242600"},{"key":"ref16","first-page":"7793","article-title":"Beyond homophily in graph neural networks: Current limitations and effective designs","volume-title":"Proc. NeurIPS","volume":"33","author":"Zhu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17332"},{"key":"ref18","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. ICLR","author":"Kipf"},{"key":"ref19","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. ICLR","author":"Veli\u010dkovi\u0107"},{"key":"ref20","first-page":"1","article-title":"Geom-GCN: Geometric graph convolutional networks","volume-title":"Proc. ICLR","author":"Pei"},{"key":"ref21","first-page":"10654","article-title":"Universal graph convolutional networks","volume-title":"Proc. NeurIPS","volume":"34","author":"Jin"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16514"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220078"},{"key":"ref24","article-title":"Fast gradient attack on network embedding","author":"Chen","year":"2018","journal-title":"arXiv:1809.02797"},{"key":"ref25","first-page":"1115","article-title":"Adversarial attack on graph structured data","volume-title":"Proc. ICML","author":"Dai"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539418"},{"key":"ref27","article-title":"GARNET: Reduced-rank topology learning for robust and scalable graph neural networks","volume-title":"Proc. LoG","author":"Deng"},{"key":"ref28","article-title":"Heterophily and graph neural networks: Past, present and future","author":"Zhu","year":"2023","journal-title":"IEEE Data Eng. Bull."},{"key":"ref29","article-title":"A survey on learning from graphs with heterophily: Recent advances and future directions","author":"Gong","year":"2024","journal-title":"arXiv:2401.09769"},{"key":"ref30","article-title":"The heterophilic graph learning handbook: Benchmarks, models, theoretical analysis, applications and challenges","author":"Luan","year":"2024","journal-title":"arXiv:2407.09618"},{"key":"ref31","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. ICML","author":"Wu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482487"},{"key":"ref33","article-title":"Ordered GNN: Ordering message passing to deal with heterophily and over-smoothing","author":"Song","year":"2022","journal-title":"arXiv:2302.01524"},{"key":"ref34","first-page":"4694","article-title":"EvenNet: Ignoring odd-hop neighbors improves robustness of graph neural networks","volume-title":"Proc. NeurIPS","volume":"35","author":"Lei"},{"key":"ref35","first-page":"42492","article-title":"Finding the missing-half: Graph complementary learning for homophily-prone and heterophily-prone graphs","volume-title":"Proc. ICML","author":"Zheng"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3257325"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124217"},{"key":"ref38","article-title":"Adaptive universal generalized pagerank graph neural network","author":"Chien","year":"2020","journal-title":"arXiv:2006.07988"},{"key":"ref39","article-title":"Is heterophily a real nightmare for graph neural networks to do node classification?","author":"Luan","year":"2021","journal-title":"arXiv:2109.05641"},{"key":"ref40","first-page":"4751","article-title":"Diverse message passing for attribute with heterophily","volume-title":"Proc. NeurIPS","volume":"34","author":"Yang"},{"key":"ref41","first-page":"17375","article-title":"GOAT: A global transformer on large-scale graphs","volume-title":"Proc. ICML","author":"Kong"},{"key":"ref42","first-page":"40078","article-title":"Multi-track message passing: Tackling oversmoothing and oversquashing in graph learning via preventing heterophily mixing","volume-title":"Proc. ICML","author":"Pei"},{"key":"ref43","first-page":"1","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. NeurIPS","volume":"30","author":"Hamilton"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447566"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1211-x"},{"key":"ref46","article-title":"A survey of adversarial learning on graphs","author":"Chen","year":"2020","journal-title":"arXiv:2003.05730"},{"key":"ref47","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. ICML","author":"Xu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2016.2586971"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1093\/comnet\/cnab014"},{"key":"ref52","volume-title":"SNAP datasets: Stanford large network dataset collection","author":"Leskovec","year":"2014"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557108"},{"key":"ref54","first-page":"1","article-title":"Adversarial training for graph neural networks: Pitfalls, solutions, and new directions","volume-title":"Proc. NeurIPS","volume":"36","author":"Gosch"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8208-z"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9338-y"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11006331\/10937261.pdf?arnumber=10937261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T17:58:08Z","timestamp":1747677488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10937261\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":56,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3548860","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}