{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:02:00Z","timestamp":1775743320356,"version":"3.50.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0725001"],"award-info":[{"award-number":["2023YFF0725001"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92370204"],"award-info":[{"award-number":["92370204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou-HKUST(GZ) Joint Funding Program","award":["2023A03J0008"],"award-info":[{"award-number":["2023A03J0008"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M750154"],"award-info":[{"award-number":["2024M750154"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M741849"],"award-info":[{"award-number":["2023M741849"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010819","name":"Education Bureau of Guangzhou Municipality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tnnls.2024.3442270","type":"journal-article","created":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T14:03:56Z","timestamp":1725631436000},"page":"8743-8756","source":"Crossref","is-referenced-by-count":9,"title":["Handling Over-Smoothing and Over-Squashing in Graph Convolution With Maximization Operation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3947-4153","authenticated-orcid":false,"given":"Dazhong","family":"Shen","sequence":"first","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5354-8630","authenticated-orcid":false,"given":"Chuan","family":"Qin","sequence":"additional","affiliation":[{"name":"PBC School of Finance, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4570-643X","authenticated-orcid":false,"given":"Hengshu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6016-6465","authenticated-orcid":false,"given":"Hui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the bottleneck of graph neural networks and its practical implications","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Alon"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5393"},{"key":"ref3","first-page":"2528","article-title":"Understanding oversquashing in GNNs through the lens of effective resistance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Black"},{"key":"ref4","first-page":"1407","article-title":"GRAND: Graph neural diffusion","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chamberlain"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103709"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645326"},{"key":"ref7","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref8","first-page":"19314","article-title":"Iterative deep graph learning for graph neural networks: Better and robust node embeddings","volume-title":"Proc. NIPS","volume":"33","author":"Chen"},{"key":"ref9","first-page":"1","article-title":"AGNN: Alternating graph-regularized neural networks to alleviate over-smoothing","author":"Chen","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref11","first-page":"7865","article-title":"On over-squashing in message passing neural networks: The impact of width, depth, and topology","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Di Giovanni"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599894"},{"key":"ref13","first-page":"1","article-title":"Mitigating over-smoothing and over-squashing using augmentations of forman-RICCI curvature","volume-title":"Proc. Learn. Graphs Conf.","author":"Fesser"},{"key":"ref14","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. 34th Int. Conf. Mach. Learning","volume":"70","author":"Gilmer"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614997"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3028705"},{"key":"ref17","first-page":"12252","article-title":"DRew: Dynamically rewired message passing with delay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gutteridge"},{"key":"ref18","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0378-8733(83)90021-7"},{"key":"ref20","article-title":"OGB-LSC: A large-scale challenge for machine learning on graphs","author":"Hu","year":"2021","journal-title":"arXiv:2103.09430"},{"key":"ref21","first-page":"1","article-title":"CGNN: A compatibility-aware graph neural network for social media bot detection","author":"Huang","year":"2024","journal-title":"IEEE Trans. Computat. Social Syst."},{"key":"ref22","article-title":"Tackling over-smoothing for general graph convolutional networks","author":"Huang","year":"2020","journal-title":"arXiv:2008.09864"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25553"},{"key":"ref24","article-title":"Spectral graph pruning against over-squashing and over-smoothing","author":"Jamadandi","year":"2024","journal-title":"arXiv:2404.04612"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.03.022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687439"},{"key":"ref27","article-title":"FoSR: First-order spectral rewiring for addressing over-squashing in GNNs","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Karhadkar"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref29","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref30","article-title":"Predict then propagate: Combining neural networks with personalized pagerank for classification on graphs","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Klicpera"},{"key":"ref31","first-page":"13354","article-title":"Diffusion improves graph learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Klicpera"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05622-4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3532611"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074057"},{"key":"ref35","first-page":"1","article-title":"Another perspective of over-smoothing: Alleviating semantic over-smoothing in deep GNNs","author":"Li","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3315284"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583269"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref40","first-page":"1","article-title":"SkipNode: On alleviating performance degradation for deep graph convolutional networks","author":"Lu","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref41","first-page":"25956","article-title":"Revisiting over-smoothing and over-squashing using ollivier-ricci curvature","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref42","article-title":"Graph neural networks exponentially lose expressive power for node classification","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Oono"},{"key":"ref43","article-title":"The pagerank citation ranking: Bringing order to the web","author":"Page","year":"1999"},{"key":"ref44","article-title":"Geom-GCN: Geometric graph convolutional networks","author":"Pei","year":"2020","journal-title":"arXiv:2002.05287"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10465-9"},{"key":"ref46","article-title":"A comprehensive survey of artificial intelligence techniques for talent analytics","author":"Qin","year":"2023","journal-title":"arXiv:2307.03195"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3604552"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3349397"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1093\/comnet\/cnab014"},{"key":"ref51","article-title":"Few-shot learning with graph neural networks","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Satorras"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref54","first-page":"14681","article-title":"Topic modeling revisited: A document graph-based neural network perspective","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"34","author":"Shen"},{"key":"ref55","first-page":"1","article-title":"Graph rewiring and preprocessing for graph neural networks based on effective resistance","author":"Shen","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-22215-y"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557108"},{"key":"ref58","article-title":"Understanding over-squashing and bottlenecks on graphs via curvature","author":"Topping","year":"2021","journal-title":"arXiv:2111.14522"},{"key":"ref59","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"issue":"3","key":"ref60","first-page":"4","article-title":"Deep graph infomax","volume-title":"Proc. ICLR","volume":"2","author":"Velickovic"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290649"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/qss_a_00021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"ref64","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657724"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref67","article-title":"How powerful are graph neural networks?","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref68","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref69","first-page":"123","article-title":"Tackling over-smoothing in graph convolutional networks with EM-based joint topology optimization and node classification","volume":"9","author":"Yang","year":"2023","journal-title":"IEEE Trans. Signal Inf. Process. Netw."},{"key":"ref70","first-page":"10238","article-title":"Graph denoising diffusion for inverse protein folding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yi"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352640"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671711"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1086\/jar.33.4.3629752"},{"key":"ref74","first-page":"19665","article-title":"Decoupling the depth and scope of graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zeng"},{"key":"ref75","article-title":"GraphSAINT: Graph sampling based inductive learning method","author":"Zeng","year":"2019","journal-title":"arXiv:1907.04931"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3239038"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380299"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467388"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645682"},{"key":"ref80","first-page":"20321","article-title":"Node dependent local smoothing for scalable graph learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref81","article-title":"PairNorm: Tackling oversmoothing in GNNs","author":"Zhao","year":"2019","journal-title":"arXiv:1909.12223"},{"key":"ref82","first-page":"4917","article-title":"Towards deeper graph neural networks with differentiable group normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhou"},{"key":"ref83","article-title":"Simple spectral graph convolution","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Zhu"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10982361\/10669089.pdf?arnumber=10669089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:54Z","timestamp":1764959994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10669089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":83,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3442270","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}