{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T09:45:54Z","timestamp":1781257554855,"version":"3.54.1"},"reference-count":142,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72421002"],"award-info":[{"award-number":["72421002"]}],"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":["72025405"],"award-info":[{"award-number":["72025405"]}],"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":["62206303"],"award-info":[{"award-number":["62206303"]}],"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":["U23A20296"],"award-info":[{"award-number":["U23A20296"]}],"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":["62272469"],"award-info":[{"award-number":["62272469"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2023RC3009"],"award-info":[{"award-number":["2023RC3009"]}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2023RC1007"],"award-info":[{"award-number":["2023RC1007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tkde.2024.3523700","type":"journal-article","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:38:38Z","timestamp":1735587518000},"page":"1455-1474","source":"Crossref","is-referenced-by-count":23,"title":["The Expressive Power of Graph Neural Networks: A Survey"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9889-5292","authenticated-orcid":false,"given":"Bingxu","family":"Zhang","sequence":"first","affiliation":[{"name":"Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3138-1104","authenticated-orcid":false,"given":"Changjun","family":"Fan","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4780-3890","authenticated-orcid":false,"given":"Shixuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuihua","family":"Huang","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6339-0219","authenticated-orcid":false,"given":"Xiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2937-3065","authenticated-orcid":false,"given":"Jincai","family":"Huang","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7547-8000","authenticated-orcid":false,"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref2","first-page":"2688","article-title":"Neural relational inference for interacting systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kipf"},{"key":"ref3","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330989"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref6","article-title":"Reinforcement learning based graph-to-sequence model for natural question generation","author":"Chen","year":"2019"},{"key":"ref7","first-page":"7113","article-title":"Constrained generation of semantically valid graphs via regularizing variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389268"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3335485"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3199201"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01055"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004311"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3200964"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435055"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/ac2fbd"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/533"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614917"},{"key":"ref22","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF02134016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"ref25","first-page":"4363","article-title":"On the universality of invariant networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maron"},{"key":"ref26","article-title":"Expressive power of invariant and equivariant graph neural networks","author":"Azizian","year":"2020"},{"key":"ref27","first-page":"7092","article-title":"Universal invariant and equivariant graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Keriven"},{"key":"ref28","article-title":"Graph isomorphisms in quasi-polynomial time","author":"Helfgott","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/1024022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/89.817450"},{"key":"ref31","first-page":"82","article-title":"Graph matching: Theoretical foundations, algorithms, and applications","volume-title":"Proc. Vis. Interface","volume":"2000","author":"Bunke"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00284"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/2273574"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"ref35","first-page":"21824","article-title":"Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Morris"},{"key":"ref36","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"ref37","first-page":"5868","article-title":"On the equivalence between graph isomorphism testing and function approximation with GNNs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref38","article-title":"A survey on the expressive power of graph neural networks","author":"Sato","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449953"},{"key":"ref40","first-page":"1","article-title":"Analyzing the expressive power of graph neural networks in a spectral perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Balcilar"},{"key":"ref41","article-title":"Graph neural networks are more powerful than we think","author":"Kanatsoulis","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1023\/A:1005245900406"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF01305232"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-11321-5_2"},{"key":"ref45","first-page":"599","article-title":"Breaking the limits of message passing graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Balcilar"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LICS52264.2021.9470677"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3442322.3442324"},{"key":"ref48","first-page":"1","article-title":"The logical expressiveness of graph neural networks","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Barcel\u00f3"},{"key":"ref49","first-page":"1","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9048920"},{"key":"ref52","article-title":"Combining generative and discriminative models for hybrid inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Satorras"},{"key":"ref53","first-page":"13802","article-title":"Learning combinatorial optimization algorithms over graphs","author":"Khalil","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"ref54","first-page":"4502","article-title":"Interaction networks for learning about objects, relations and physics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Battaglia"},{"key":"ref55","article-title":"What can neural networks reason about?","author":"Xu","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref57","article-title":"Graph neural networks exponentially lose expressive power for node classification","author":"Oono","year":"2019"},{"key":"ref58","article-title":"Revisiting graph neural networks for link prediction","author":"Zhang","year":"2020"},{"key":"ref59","article-title":"On the bottleneck of graph neural networks and its practical implications","author":"Alon","year":"2020"},{"key":"ref60","article-title":"Understanding over-squashing and bottlenecks on graphs via curvature","author":"Topping","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17283"},{"key":"ref62","first-page":"7134","article-title":"Position-aware graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref63","first-page":"3419","article-title":"Generalization and representational limits of graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Garg"},{"key":"ref64","first-page":"10383","article-title":"Can graph neural networks count substructures?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1039\/C9ME00039A"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbz042"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3004964"},{"key":"ref69","article-title":"Invariant and equivariant graph networks","author":"Maron","year":"2018"},{"key":"ref70","article-title":"Expressiveness and approximation properties of graph neural networks","author":"Geerts","year":"2022"},{"issue":"9","key":"ref71","first-page":"12","article-title":"The reduction of a graph to canonical form and the algebra which appears therein","volume":"2","author":"Weisfeiler","year":"1968","journal-title":"NTI, Ser."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1979.8"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1002\/jgt.3190010410"},{"issue":"9","key":"ref74","first-page":"2539","article-title":"Weisfeiler-Lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1137\/0209047"},{"key":"ref76","volume-title":"On Construction and Identification of Graphs","volume":"558","author":"Weisfeiler","year":"2006"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1017\/jsl.2015.28"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3542609"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"ref81","first-page":"4805","article-title":"Hierarchical graph representation learning with differentiable pooling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref82","article-title":"Graph capsule convolutional neural networks","author":"Verma","year":"2018"},{"key":"ref83","first-page":"4477","article-title":"Measuring abstract reasoning in neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref84","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Gasteiger","year":"2018"},{"key":"ref85","article-title":"SIGN: Scalable inception graph neural networks","author":"Frasca","year":"2020"},{"key":"ref86","article-title":"On graph neural networks versus graph-augmented MLPs","author":"Chen","year":"2020"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref88","article-title":"Graph neural networks are inherently good generalizers: Insights by bridging GNNs and MLPs","author":"Yang","year":"2022"},{"key":"ref89","article-title":"A gentle introduction to graph neural networks","author":"Pearce","year":"2021"},{"key":"ref90","first-page":"28191","article-title":"Equivariant polynomials for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Puny"},{"key":"ref91","first-page":"1","article-title":"Beyond Weisfeiler-Lehman: A quantitative framework for GNN expressiveness","volume-title":"Proc. Twelfth Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3220789"},{"key":"ref93","article-title":"What graph neural networks cannot learn: Depth vs width","author":"Loukas","year":"2019"},{"key":"ref94","first-page":"14143","article-title":"Building powerful and equivariant graph neural networks with structural message-passing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vignac"},{"key":"ref95","article-title":"Neural sheaf diffusion: A topological perspective on heterophily and oversmoothing in GNNs","author":"Bodnar","year":"2022"},{"key":"ref96","article-title":"How hard is graph isomorphism for graph neural networks","author":"Loukas","year":"2020"},{"key":"ref97","first-page":"3636","article-title":"Natural graph networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"de Haan"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403177"},{"key":"ref99","first-page":"4040","article-title":"A. collective learning framework to boost GNN expressiveness for node classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hang"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570457"},{"key":"ref101","article-title":"Twin weisfeiler-lehman: High expressive GNNs for graph classification","author":"Wang","year":"2022"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/294"},{"key":"ref103","first-page":"4663","article-title":"Relational pooling for graph representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Murphy"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/291"},{"key":"ref105","first-page":"4465","article-title":"Distance encoding: Design provably more powerful neural networks for graph representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref106","article-title":"Equivariant and stable positional encoding for more powerful graph neural networks","author":"Wang","year":"2022"},{"key":"ref107","article-title":"Rethinking the expressive power of GNNs via graph biconnectivity","author":"Zhang","year":"2023"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3112746"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26318"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3154319"},{"key":"ref111","first-page":"1","article-title":"A new perspective on","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wijesinghe"},{"key":"ref112","article-title":"From stars to subgraphs: Uplifting any GNN with local structure awareness","author":"Zhao","year":"2021"},{"key":"ref113","first-page":"15734","article-title":"Nested graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref114","first-page":"1026","article-title":"Weisfeiler and Lehman go topological: Message passing simplicial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bodnar"},{"key":"ref115","article-title":"Equivariant subgraph aggregation networks","author":"Bevilacqua","year":"2021"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.07.008"},{"key":"ref117","first-page":"4776","article-title":"How powerful are k-hop message passing graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref118","first-page":"9029","article-title":"Extending the design space of graph neural networks by rethinking folklore Weisfeiler-Lehman","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29463"},{"key":"ref120","first-page":"15413","article-title":"Understanding the representation power of graph neural networks in learning graph topology","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dehmamy"},{"key":"ref121","article-title":"Geom-GCN: Geometric graph convolutional networks","author":"Pei","year":"2020"},{"key":"ref122","article-title":"Going deeper into permutation-sensitive graph neural networks","author":"Huang","year":"2022"},{"key":"ref123","first-page":"2153","article-title":"Provably powerful graph networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Maron"},{"key":"ref124","article-title":"The expressive power of kth-order invariant graph networks","author":"Geerts","year":"2020"},{"key":"ref125","article-title":"Understanding and extending subgraph GNNs by rethinking their symmetries","author":"Frasca","year":"2022"},{"key":"ref126","first-page":"4081","article-title":"Approximation ratios of graph neural networks for combinatorial problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sato"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976700.38"},{"key":"ref128","article-title":"Computational algebraic topology lecture notes","author":"Nanda","year":"2021"},{"key":"ref129","first-page":"42","article-title":"On weisfeiler-leman invariance: Subgraph counts and related graph properties","author":"Vikraman","year":"2020","journal-title":"J. Comput. Syst. Sci."},{"key":"ref130","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":"ref131","article-title":"Multi-hop attention graph neural network","author":"Wang","year":"2020"},{"key":"ref132","article-title":"Adaptive universal generalized pagerank graph neural network","author":"Chien","year":"2020"},{"key":"ref133","article-title":"Graph convolutions that can finally model local structure","author":"Brossard","year":"2020"},{"key":"ref134","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref135","article-title":"Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs","author":"Murphy","year":"2018"},{"key":"ref136","first-page":"21997","article-title":"DropGNN: Random dropouts increase the expressiveness of graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Papp"},{"key":"ref137","article-title":"A theoretical comparison of graph neural network extensions","author":"Papp","year":"2022"},{"key":"ref138","first-page":"1713","article-title":"Reconstruction for powerful graph representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cotta"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.42"},{"key":"ref140","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1021\/ci0342472"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2023.102538"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/10855162\/10818675.pdf?arnumber=10818675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:51:50Z","timestamp":1738090310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10818675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":142,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3523700","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}