{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T07:04:58Z","timestamp":1779692698584,"version":"3.53.1"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011025","name":"Government of Western Australia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011025","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210102273"],"award-info":[{"award-number":["DP210102273"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108869","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T16:03:16Z","timestamp":1773763396000},"page":"108869","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Permutation-Invariant graph partitioning: How graph neural networks capture structural interactions?"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3635-4818","authenticated-orcid":false,"given":"Asela","family":"Hevapathige","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9504-4273","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108869_bib0001","series-title":"International conference on machine learning","article-title":"Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","author":"Abu-El-Haija","year":"2019"},{"key":"10.1016\/j.neunet.2026.108869_bib0002","article-title":"Large scale networks fingerprinting and visualization using the k-core decomposition","author":"Alvarez-Hamelin","year":"2005","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0003","series-title":"International conference on machine learning","article-title":"Breaking the limits of message passing graph neural networks","author":"Balcilar","year":"2021"},{"key":"10.1016\/j.neunet.2026.108869_bib0004","first-page":"25280","article-title":"Graph neural networks with local graph parameters","volume":"34","author":"Barcel\u00f3","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0005","series-title":"International conference on machine learning","article-title":"Directional graph networks","author":"Beaini","year":"2021"},{"key":"10.1016\/j.neunet.2026.108869_bib0006","article-title":"Equivariant subgraph aggregation networks","author":"Bevilacqua","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.neunet.2026.108869_bib0007","article-title":"Weisfeiler and lehman go cellular: Cw networks","author":"Bodnar","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0008","article-title":"Improving graph neural network expressivity via subgraph isomorphism counting","author":"Bouritsas","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"10.1016\/j.neunet.2026.108869_bib0009","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/BF01305232","article-title":"An optimal lower bound on the number of variables for graph identification","volume":"12","author":"Cai","year":"1992","journal-title":"Combinatorica"},{"key":"10.1016\/j.neunet.2026.108869_bib0010","article-title":"Can graph neural networks count substructures?","author":"Chen","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0011","series-title":"Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","article-title":"Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks","author":"Chiang","year":"2019"},{"key":"10.1016\/j.neunet.2026.108869_bib0012","article-title":"Reconstruction for powerful graph representations","author":"Cotta","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1\u20132","key":"10.1016\/j.neunet.2026.108869_bib0013","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0004-3702(00)00004-7","article-title":"Learning to construct knowledge bases from the world wide web","volume":"118","author":"Craven","year":"2000","journal-title":"Artificial Intelligence"},{"issue":"43","key":"10.1016\/j.neunet.2026.108869_bib0014","first-page":"1","article-title":"Benchmarking graph neural networks","volume":"24","author":"Dwivedi","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108869_bib0015","article-title":"How powerful are k-hop message passing graph neural networks","author":"Feng","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0016","first-page":"31376","article-title":"Understanding and extending subgraph gnns by rethinking their symmetries","volume":"35","author":"Frasca","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0017","series-title":"Graph partition neural networks for semi-supervised classification","author":"Gaunt","year":"2018"},{"key":"10.1016\/j.neunet.2026.108869_bib0018","series-title":"International conference on machine learning","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"10.1016\/j.neunet.2026.108869_bib0019","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0020","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5299","article-title":"Learnable graph matching: Incorporating graph partitioning with deep feature learning for multiple object tracking","author":"He","year":"2021"},{"key":"10.1016\/j.neunet.2026.108869_bib0021","article-title":"Topological graph neural networks","author":"Horn","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.neunet.2026.108869_bib0022","article-title":"Open graph benchmark: Datasets for machine learning on graphs","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0023","article-title":"Boosting the cycle counting power of graph neural networks with i2-GNNs","author":"Huang","year":"2023","journal-title":"International Conference on Learning Representations"},{"issue":"7","key":"10.1016\/j.neunet.2026.108869_bib0024","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1021\/ci3001277","article-title":"Zinc: A free tool to discover chemistry for biology","volume":"52","author":"Irwin","year":"2012","journal-title":"Journal of Chemical Information and Modeling"},{"key":"10.1016\/j.neunet.2026.108869_bib0025","series-title":"Forty-first international conference on machine learning","article-title":"Homomorphism counts for graph neural networks: All about that basis","author":"Jin","year":"2024"},{"key":"10.1016\/j.neunet.2026.108869_bib0026","series-title":"International conference on learning representations","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.neunet.2026.108869_bib0027","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.neunet.2026.108869_bib0028","series-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","first-page":"3271","article-title":"Large-scale network embedding in apache spark","author":"Lin","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2026.108869_bib0029","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/s00778-019-00587-4","article-title":"The core decomposition of networks: Theory, algorithms and applications","volume":"29","author":"Malliaros","year":"2020","journal-title":"The VLDB Journal"},{"key":"10.1016\/j.neunet.2026.108869_bib0030","article-title":"Provably powerful graph networks","author":"Maron","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0031","series-title":"International conference on machine learning","article-title":"On the universality of invariant networks","author":"Maron","year":"2019"},{"key":"10.1016\/j.neunet.2026.108869_bib0032","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.jsc.2013.09.003","article-title":"Practical graph isomorphism, II","volume":"60","author":"McKay","year":"2014","journal-title":"Journal of Symbolic Computation"},{"key":"10.1016\/j.neunet.2026.108869_bib0033","series-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","article-title":"Degnn: Improving graph neural networks with graph decomposition","author":"Miao","year":"2021"},{"key":"10.1016\/j.neunet.2026.108869_bib0034","article-title":"Tudataset: A collection of benchmark datasets for learning with graphs","author":"Morris","year":"2020","journal-title":"ICML workshop \u2019Graph Representation Learning and Beyond\u2019"},{"key":"10.1016\/j.neunet.2026.108869_bib0035","article-title":"Weisfeiler and leman go sparse: Towards scalable higher-order graph embeddings","author":"Morris","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0036","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Weisfeiler and leman go neural: Higher-order graph neural networks","author":"Morris","year":"2019"},{"key":"10.1016\/j.neunet.2026.108869_bib0037","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1016\/j.neucom.2022.09.096","article-title":"Graph neural networks meet with distributed graph partitioners and reconciliations","volume":"518","author":"Mu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108869_bib0038","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.neunet.2020.07.008","article-title":"K-hop graph neural networks","volume":"130","author":"Nikolentzos","year":"2020","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108869_bib0039","article-title":"Geom-gcn: Geometric graph convolutional networks","author":"Pei","year":"2020","journal-title":"International Conference on Learning Representations"},{"issue":"3","key":"10.1016\/j.neunet.2026.108869_bib0040","article-title":"Collective classification in network data","volume":"29","author":"Prithviraj","year":"2008","journal-title":"AI Magazine"},{"key":"10.1016\/j.neunet.2026.108869_bib0041","unstructured":"Sato, R. (2020). A survey on the expressive power of graph neural networks. arXiv preprint arXiv: 2003.04078."},{"issue":"1","key":"10.1016\/j.neunet.2026.108869_bib0042","doi-asserted-by":"crossref","first-page":"8340","DOI":"10.1038\/s41598-019-44907-8","article-title":"On neighbourhood degree sequences of complex networks","volume":"9","author":"Smith","year":"2019","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2026.108869_bib0043","series-title":"International conference on learning representations","article-title":"Graph attention networks","author":"Velickovic","year":"2018"},{"issue":"2","key":"10.1016\/j.neunet.2026.108869_bib0044","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3589288","article-title":"Scalable and efficient full-graph gnn training for large graphs","volume":"1","author":"Wan","year":"2023","journal-title":"Proceedings of the ACM on Management of Data"},{"key":"10.1016\/j.neunet.2026.108869_bib0045","series-title":"International conference on learning representations","article-title":"Glass: Gnn with labeling tricks for subgraph representation learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108869_bib0046","series-title":"The first learning on graphs conference","article-title":"Towards efficient and expressive GNNs for graph classification via subgraph-aware weisfeiler-lehman","author":"Wang","year":"2022"},{"issue":"9","key":"10.1016\/j.neunet.2026.108869_bib0047","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, Series"},{"issue":"9","key":"10.1016\/j.neunet.2026.108869_bib0048","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, Series"},{"key":"10.1016\/j.neunet.2026.108869_bib0049","series-title":"International conference on learning representations","article-title":"A new perspective on how graph neural networks go beyond weisfeiler-lehman?","author":"Wijesinghe","year":"2022"},{"key":"10.1016\/j.neunet.2026.108869_bib0050","unstructured":"Xu, H., Chen, R., Bai, Y., Feng, J., Duan, Z., Luo, K., Sun, Y., & Wang, W. (2020). Hierarchical and fast graph similarity computation via graph coarsening and deep graph learning. arXiv preprint arXiv: 2005.07115."},{"key":"10.1016\/j.neunet.2026.108869_bib0051","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.neucom.2021.01.068","article-title":"Graph partitioning and graph neural network based hierarchical graph matching for graph similarity computation","volume":"439","author":"Xu","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108869_bib0052","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"16173","article-title":"Union subgraph neural networks","volume":"vol. 38","author":"Xu","year":"2024"},{"key":"10.1016\/j.neunet.2026.108869_bib0053","series-title":"International conference on learning representations","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"10.1016\/j.neunet.2026.108869_bib0054","series-title":"Proceedings of the 28th ACM international conference on architectural support for programming languages and operating systems, volume 2","first-page":"103","article-title":"Betty: Enabling large-scale gnn training with batch-level graph partitioning","author":"Yang","year":"2023"},{"key":"10.1016\/j.neunet.2026.108869_bib0055","unstructured":"Ye, Y., Lian, X., & Chen, M.. Efficient exact subgraph matching via GNN-based path dominance embedding."},{"key":"10.1016\/j.neunet.2026.108869_bib0056","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Identity-aware graph neural networks","author":"You","year":"2021"},{"key":"10.1016\/j.neunet.2026.108869_bib0057","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11129","article-title":"Substructure aware graph neural networks","volume":"vol. 37","author":"Zeng","year":"2023"},{"key":"10.1016\/j.neunet.2026.108869_bib0058","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2024.3454328","article-title":"The expressive power of graph neural networks: A survey","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2026.108869_bib0059","series-title":"The twelfth international conference on learning representations","article-title":"Beyond weisfeiler-lehman: A quantitative framework for GNN expressiveness","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.108869_bib0060","first-page":"15734","article-title":"Nested graph neural networks","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108869_bib0061","article-title":"From stars to subgraphs: Uplifting any GNN with local structure awareness","author":"Zhao","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.neunet.2026.108869_bib0062","article-title":"A practical, progressively-expressive GNN","author":"Zhao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003308?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003308?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:37:43Z","timestamp":1779691063000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003308"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":62,"alternative-id":["S0893608026003308"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108869","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Permutation-Invariant graph partitioning: How graph neural networks capture structural interactions?","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108869","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108869"}}