{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T13:23:41Z","timestamp":1793193821984,"version":"4.5.0"},"reference-count":73,"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":"National Key Research and Development Program of China","award":["2022ZD0116500"],"award-info":[{"award-number":["2022ZD0116500"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276186"],"award-info":[{"award-number":["62276186"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61925602"],"award-info":[{"award-number":["61925602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222608"],"award-info":[{"award-number":["62222608"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tianjin Natural Science Funds for Distinguished Young Scholar","award":["23JCJQJC00270"],"award-info":[{"award-number":["23JCJQJC00270"]}]},{"name":"Chinese Association for Artificial Intelligence (CAAI) Huawei MindSpore Open Fund","award":["CAAIXSJLJJ-2022-010C"],"award-info":[{"award-number":["CAAIXSJLJJ-2022-010C"]}]},{"name":"Haihe Laboratory of Information Technology Application Innovation","award":["22HHXCJC00002"],"award-info":[{"award-number":["22HHXCJC00002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3390249","type":"journal-article","created":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T13:41:38Z","timestamp":1714398098000},"page":"6395-6406","source":"Crossref","is-referenced-by-count":9,"title":["CCP-GNN: Competitive Covariance Pooling for Improving Graph Neural Networks"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4310-9140","authenticated-orcid":false,"given":"Pengfei","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Dong","sequence":"additional","affiliation":[{"name":"Baidu Company, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8095","authenticated-orcid":false,"given":"Qinghua","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4444-7811","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3765-9787","authenticated-orcid":false,"given":"Qilong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref2","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref3","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16514"},{"key":"ref5","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref6","first-page":"1","article-title":"Variational graph auto-encoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshops","author":"Kipf"},{"key":"ref7","first-page":"5171","article-title":"Link prediction based on graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5693"},{"key":"ref9","first-page":"1","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref10","first-page":"3734","article-title":"Self-attention graph pooling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3495645"},{"key":"ref12","first-page":"1204","article-title":"GraphNorm: A principled approach to accelerating graph neural network training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cai"},{"key":"ref13","first-page":"1","article-title":"Wasserstein embedding for graph learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kolouri"},{"key":"ref14","first-page":"723","article-title":"Graph convolutional networks with EigenPooling","volume-title":"Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining","author":"Ma"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313668"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2999032"},{"key":"ref17","first-page":"1","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref18","first-page":"1","article-title":"Tudataset: A collection of benchmark datasets for learning with graphs","volume-title":"Proc. Int. Conf. Mach. Learn. Workshops","author":"Morris"},{"key":"ref19","first-page":"1993","article-title":"Diffusion-convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Atwood"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"ref21","first-page":"1","article-title":"Gated graph sequence neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref22","first-page":"589","article-title":"Region covariance: A fast descriptor for detection and classification","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Tuzel"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974833"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b00959"},{"key":"ref26","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Duvenaud"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/11566465_15"},{"issue":"1","key":"ref28","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s11263-005-3222-z","article-title":"A Riemannian framework for tensor computing","volume":"66","author":"Pennec","year":"2006","journal-title":"Int. J. Comput. Vis."},{"key":"ref29","article-title":"DeeperGCN: All you need to train deeper GCNs","author":"Li","year":"2020","journal-title":"arXiv:2006.07739"},{"key":"ref30","first-page":"3837","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Defferrard"},{"key":"ref31","article-title":"Hierarchical graph pooling with structure learning","author":"Zhang","year":"2019","journal-title":"arXiv:1911.05954"},{"key":"ref32","first-page":"1","article-title":"Order matters: Sequence to sequence for sets","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Vinyals"},{"key":"ref33","first-page":"1","article-title":"Accurate learning of graph representations with graph multiset pooling","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Baek"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1115"},{"key":"ref35","first-page":"1","article-title":"Memory-based graph networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ahmadi"},{"key":"ref36","first-page":"1","article-title":"Structpool: Structured graph pooling via conditional random fields","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yuan"},{"key":"ref37","first-page":"2083","article-title":"Graph U-Nets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao"},{"key":"ref38","first-page":"1","article-title":"Towards graph pooling by edge contraction","volume-title":"Proc. Int. Conf. Mach. Learn. Workshops","author":"Diehl"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.339"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.228"},{"key":"ref41","first-page":"144","article-title":"A new metric on the manifold of kernel matrices with application to matrix geometric means","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sra"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898717778","volume-title":"Functions of Matrices: Theory and Computation","author":"Higham","year":"2008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btg130"},{"key":"ref45","article-title":"Benchmarking graph neural networks","author":"Dwivedi","year":"2020","journal-title":"arXiv:2003.00982"},{"key":"ref46","first-page":"1","article-title":"Principal neighbourhood aggregation for graph nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Corso"},{"key":"ref47","first-page":"13266","article-title":"Representing long-range context for graph neural networks with global attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"issue":"1","key":"ref48","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"issue":"2","key":"ref50","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: A benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"key":"ref51","first-page":"2014","article-title":"Learning convolutional neural networks for graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Niepert"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"ref53","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref54","first-page":"1","article-title":"Fast graph representation learning with PyTorch geometric","volume-title":"Proc. Int. Conf. Learn. Represent. Workshops","author":"Fey"},{"key":"ref55","first-page":"1","article-title":"Rethinking pooling in graph neural networks","author":"Mesquita","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.689"},{"key":"ref57","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref58","article-title":"FLAG: Adversarial data augmentation for graph neural networks","author":"Kong","year":"2020","journal-title":"arXiv:2010.09891"},{"key":"ref59","article-title":"Improving graph neural network expressivity via subgraph isomorphism counting","author":"Bouritsas","year":"2020","journal-title":"arXiv:2006.09252"},{"key":"ref60","first-page":"1","article-title":"Hierarchical inter-nessage passing for learning on molecular graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fey"},{"key":"ref61","first-page":"748","article-title":"Directional graph networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Beani"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539249"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583386"},{"key":"ref64","first-page":"1","article-title":"Universal prompt tuning for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fang"},{"key":"ref65","article-title":"Are powerful graph neural nets necessary? A dissection on graph classification","author":"Chen","year":"2019","journal-title":"arXiv:1905.04579"},{"key":"ref66","article-title":"Graph capsule convolutional neural networks","author":"Verma","year":"2018","journal-title":"arXiv:1805.08090"},{"key":"ref67","first-page":"1","article-title":"Capsule graph neural network","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xinyi"},{"key":"ref68","first-page":"1","article-title":"Factorizable graph convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"issue":"9","key":"ref69","first-page":"2539","article-title":"Weisfeiler-lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref70","volume-title":"RDKit: Open-Source Cheminformatics","author":"Landrum","year":"2006"},{"key":"ref71","article-title":"Residual gated graph ConvNets","author":"Bresson","year":"2017","journal-title":"arXiv:1711.07553"},{"key":"ref72","first-page":"28877","article-title":"Do transformers really perform bad for graph representation?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86365-4_17"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10509794.pdf?arnumber=10509794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:05Z","timestamp":1764959945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10509794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":73,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3390249","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}