{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:13:12Z","timestamp":1778249592256,"version":"3.51.4"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"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-017"},{"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"},{"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-012"},{"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-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133713","type":"journal-article","created":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T15:24:48Z","timestamp":1776525888000},"page":"133713","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-granularity graph refinement via granular ball for graph classification"],"prefix":"10.1016","volume":"686","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0812-2347","authenticated-orcid":false,"given":"Jinyuan","family":"Ni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuyin","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4570-5749","authenticated-orcid":false,"given":"Gaojie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.neucom.2026.133713_bib0005","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1145\/116873.116880","article-title":"Voronoi diagrams\u2014a survey of a fundamental geometric data structure","volume":"23","author":"Aurenhammer","year":"1991","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.133713_bib0010","series-title":"International Conference on Learning Representations","article-title":"Accurate learning of graph representations with graph multiset pooling","author":"Baek","year":"2021"},{"key":"10.1016\/j.neucom.2026.133713_bib0015","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"874","article-title":"Spectral clustering with graph neural networks for graph pooling","author":"Bianchi","year":"2020"},{"key":"10.1016\/j.neucom.2026.133713_bib0020","series-title":"Fifth IEEE International Conference on Data Mining","first-page":"8","article-title":"Shortest-path kernels on graphs","author":"Borgwardt","year":"2005"},{"key":"10.1016\/j.neucom.2026.133713_bib0025","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1017\/ATSIP.2020.13","article-title":"Graph representation learning: a survey","volume":"9","author":"Chen","year":"2020","journal-title":"APSIPA Trans. Signal Inf. Process."},{"issue":"3","key":"10.1016\/j.neucom.2026.133713_bib0030","first-page":"275","article-title":"On human cognitive processing mechanisms","volume":"10","author":"Chen","year":"1982","journal-title":"Cognitive Science Journal"},{"key":"10.1016\/j.neucom.2026.133713_bib0035","series-title":"International Conference on Machine Learning","first-page":"5257","article-title":"A gromov-wasserstein geometric view of spectrum-preserving graph coarsening","author":"Chen","year":"2023"},{"issue":"12","key":"10.1016\/j.neucom.2026.133713_bib0040","doi-asserted-by":"crossref","first-page":"17202","DOI":"10.1109\/TNNLS.2023.3300916","article-title":"A fast granular-ball-based density peaks clustering algorithm for large-scale data","volume":"35","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"10.1016\/j.neucom.2026.133713_bib0045","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/S0022-2836(03)00628-4","article-title":"Distinguishing enzyme structures from non-enzymes without alignments","volume":"330","author":"Dobson","year":"2003","journal-title":"J. Mol. Biol."},{"issue":"5","key":"10.1016\/j.neucom.2026.133713_bib0050","doi-asserted-by":"crossref","first-page":"9488","DOI":"10.1109\/TNNLS.2024.3413750","article-title":"Ccgib: a cross-channel graph information bottleneck principle","volume":"36","author":"Fan","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133713_bib0055","series-title":"Advances in Neural Information Processing Systems","article-title":"Inductive representation learning on large graphs","volume":"vol. 30","author":"Hamilton","year":"2017"},{"key":"10.1016\/j.neucom.2026.133713_bib0060","series-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"594","article-title":"Graphmae: self-supervised masked graph autoencoders","author":"Hou","year":"2022"},{"key":"10.1016\/j.neucom.2026.133713_bib0065","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11313","article-title":"Semi-supervised learning with graph learning-convolutional networks","author":"Jiang","year":"2019"},{"key":"10.1016\/j.neucom.2026.133713_bib0070","series-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"66","article-title":"Graph structure learning for robust graph neural networks","author":"Jin","year":"2020"},{"key":"10.1016\/j.neucom.2026.133713_bib0075","series-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"720","article-title":"Condensing graphs via one-step gradient matching","author":"Jin","year":"2022"},{"key":"10.1016\/j.neucom.2026.133713_bib0080","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"4452","article-title":"Graph coarsening with preserved spectral properties","author":"Jin","year":"2020"},{"key":"10.1016\/j.neucom.2026.133713_bib0085","first-page":"5896","article-title":"Geodesic graph neural network for efficient graph representation learning","volume":"35","author":"Kong","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"7553","key":"10.1016\/j.neucom.2026.133713_bib0090","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.neucom.2026.133713_bib0095","series-title":"ECML PKDD Workshop on Mining and Learning with Graphs","article-title":"Geometry-aware edge pooling for graph neural networks","author":"Limbeck","year":"2025"},{"key":"10.1016\/j.neucom.2026.133713_bib0100","series-title":"Proceedings of the ACM Web Conference 2022","first-page":"1601","article-title":"Compact graph structure learning via mutual information compression","author":"Liu","year":"2022"},{"issue":"116","key":"10.1016\/j.neucom.2026.133713_bib0105","first-page":"1","article-title":"Graph reduction with spectral and CUT guarantees","volume":"20","author":"Loukas","year":"2019","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"10.1016\/j.neucom.2026.133713_bib0110","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-008-5086-2","article-title":"Graph kernels based on tree patterns for molecules","volume":"75","author":"Mah\u00e9","year":"2009","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2026.133713_bib0115","author":"Morris"},{"key":"10.1016\/j.neucom.2026.133713_bib0120","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s10994-015-5517-9","article-title":"Propagation kernels: efficient graph kernels from propagated information","author":"Neumann","year":"2016","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2026.133713_bib0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2025.122748","article-title":"Multi-granularity spectral graph coarsening","volume":"726","author":"Ni","year":"2026","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133713_bib0130","series-title":"International Workshop on Frontiers in Algorithmics","first-page":"186","article-title":"Ranking of closeness centrality for large-scale social networks","author":"Okamoto","year":"2008"},{"key":"10.1016\/j.neucom.2026.133713_bib0135","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1756-0381-4-10","article-title":"Using graph theory to analyze biological networks","volume":"4","author":"Pavlopoulos","year":"2011","journal-title":"Biodata Min."},{"key":"10.1016\/j.neucom.2026.133713_bib0140","first-page":"14501","article-title":"Recipe for a general, powerful, scalable graph transformer","volume":"35","author":"Ramp\u00e1\u0161ek","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"9","key":"10.1016\/j.neucom.2026.133713_bib0145","article-title":"Weisfeiler-lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133713_bib0150","series-title":"Artificial Intelligence and Statistics","first-page":"488","article-title":"Efficient graphlet kernels for large graph comparison","author":"Shervashidze","year":"2009"},{"key":"10.1016\/j.neucom.2026.133713_bib0155","author":"Sun"},{"key":"10.1016\/j.neucom.2026.133713_bib0160","series-title":"Proceedings of the Web Conference 2021","first-page":"2081","article-title":"Sugar: subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism","author":"Sun","year":"2021"},{"issue":"6","key":"10.1016\/j.neucom.2026.133713_bib0165","doi-asserted-by":"crossref","first-page":"1906","DOI":"10.1021\/ci034143r","article-title":"Spline-fitting with a genetic algorithm: a method for developing classification structure\u2212 activity relationships","volume":"43","author":"Sutherland","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"10.1016\/j.neucom.2026.133713_bib0170","author":"Veli\u010dkovi\u0107"},{"key":"10.1016\/j.neucom.2026.133713_bib0175","article-title":"Supervised graph inference","volume":"17","author":"Vert","year":"2004","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133713_bib0180","series-title":"International Conference on Machine Learning","first-page":"10564","article-title":"Online graph dictionary learning","author":"Vincent-Cuaz","year":"2021"},{"key":"10.1016\/j.neucom.2026.133713_bib0185","series-title":"Proceedings of the International Conference on Granular Computing","first-page":"1","article-title":"Multi-granularity cognitive computing: a new paradigm for AI","author":"Wang","year":"2015"},{"key":"10.1016\/j.neucom.2026.133713_bib0190","series-title":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","first-page":"2091","article-title":"Pooling architecture search for graph classification","author":"Wei","year":"2021"},{"key":"10.1016\/j.neucom.2026.133713_bib0195","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.ins.2019.01.010","article-title":"Granular ball computing classifiers for efficient, scalable and robust learning","volume":"483","author":"Xia","year":"2019","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133713_bib0200","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12872","article-title":"Graph coarsening via supervised granular-ball for scalable graph neural network training","volume":"vol. 39","author":"Xia","year":"2025"},{"key":"10.1016\/j.neucom.2026.133713_bib0205","series-title":"International Joint Conference on Artificial Intelligence","article-title":"Gbgc: efficient and adaptive graph coarsening via granular-ball computing","author":"Xia","year":"2025"},{"issue":"9","key":"10.1016\/j.neucom.2026.133713_bib0210","doi-asserted-by":"crossref","first-page":"9743","DOI":"10.1109\/TKDE.2023.3249475","article-title":"An efficient spectral clustering algorithm based on granular-ball","volume":"35","author":"Xie","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.133713_bib0215","series-title":"International Conference on Learning Representations","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2019"},{"key":"10.1016\/j.neucom.2026.133713_bib0220","series-title":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"1365","article-title":"Deep graph kernels","author":"Yanardag","year":"2015"},{"key":"10.1016\/j.neucom.2026.133713_bib0225","series-title":"Advances in Neural Information Processing Systems","article-title":"Hierarchical graph representation learning with differentiable pooling","volume":"vol. 31","author":"Ying","year":"2018"},{"key":"10.1016\/j.neucom.2026.133713_bib0230","series-title":"Advances in Neural Information Processing Systems","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"vol. 33","author":"You","year":"2020"},{"issue":"3","key":"10.1016\/j.neucom.2026.133713_bib0235","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1002\/prot.21018","article-title":"Prediction of protein subcellular localization","volume":"64","author":"Yu","year":"2006","journal-title":"Proteins Struct. Funct. Bioinform."},{"key":"10.1016\/j.neucom.2026.133713_bib0240","first-page":"119","article-title":"The upper bound of the optimal number of clusters in fuzzy clustering","volume":"44","author":"Yu","year":"2001","journal-title":"Science in China Series: Information Sciences"},{"key":"10.1016\/j.neucom.2026.133713_bib0245","series-title":"Introduction to Graph Theory","volume":"vol. 2","author":"Zhang","year":"2006"},{"key":"10.1016\/j.neucom.2026.133713_bib0250","series-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"2515","article-title":"Improving social network embedding via new second-order continuous graph neural networks","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133713_bib0255","series-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"3422","article-title":"Contrastive cross-scale graph knowledge synergy","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133713_bib0260","first-page":"15870","article-title":"Motif-based graph self-supervised learning for molecular property prediction","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133713_bib0265","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"17042","article-title":"A twist for graph classification: optimizing causal information flow in graph neural networks","volume":"vol. 38","author":"Zhao","year":"2024"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226011100?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226011100?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T13:29:25Z","timestamp":1778246965000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226011100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":53,"alternative-id":["S0925231226011100"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133713","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-granularity graph refinement via granular ball for graph classification","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133713","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133713"}}