{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:00:06Z","timestamp":1781146806523,"version":"3.54.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":["Neural Networks"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108906","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:05:29Z","timestamp":1774883129000},"page":"108906","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Beyond pairwise dependence: A multi-filter fusion network for graph representation learning"],"prefix":"10.1016","volume":"201","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8332-9255","authenticated-orcid":false,"given":"Hui","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoguo","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108906_bib0001","series-title":"International conference on machine learning (ICML)","first-page":"21","article-title":"Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","author":"Abu-El-Haija","year":"2019"},{"key":"10.1016\/j.neunet.2026.108906_bib0002","unstructured":"Akansha, S. (2023). Over-squashing in graph neural networks: A comprehensive survey. arxiv: 2308.15568."},{"key":"10.1016\/j.neunet.2026.108906_bib0003","article-title":"Diffusion-convolutional neural networks","volume":"29","author":"Atwood","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.108906_bib0004","series-title":"International conference on learning representations (ICLR)","article-title":"Analyzing the expressive power of graph neural networks in a spectral perspective","author":"Balcilar","year":"2021"},{"key":"10.1016\/j.neunet.2026.108906_bib0005","series-title":"Transactions on machine learning research","article-title":"How expressive are transformers in spectral domain for graphs?","author":"Bastos","year":"2022"},{"key":"10.1016\/j.neunet.2026.108906_bib0006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.physrep.2020.05.004","article-title":"Networks beyond pairwise interactions: Structure and dynamics","volume":"874","author":"Battiston","year":"2020","journal-title":"Physics Reports"},{"issue":"7","key":"10.1016\/j.neunet.2026.108906_bib0007","first-page":"3496","article-title":"Graph neural networks with convolutional arma filters","volume":"44","author":"Bianchi","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2026.108906_bib0008","article-title":"Specformer: Spectral graph neural networks meet transformers","author":"Bo","year":"2023","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"10.1016\/j.neunet.2026.108906_bib0009","first-page":"2625","article-title":"Weisfeiler and lehman go cellular: Cw networks","volume":"34","author":"Bodnar","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108906_bib0010","series-title":"International conference on machine learning","first-page":"1026","article-title":"Weisfeiler and lehman go topological: Message passing simplicial networks","author":"Bodnar","year":"2021"},{"key":"10.1016\/j.neunet.2026.108906_bib0011","first-page":"23036","article-title":"A note on sparse generalized eigenvalue problem","volume":"34","author":"Cai","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"issue":"5996","key":"10.1016\/j.neunet.2026.108906_bib0012","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1126\/science.1185231","article-title":"The spread of behavior in an online social network experiment","volume":"329","author":"Centola","year":"2010","journal-title":"Science"},{"key":"10.1016\/j.neunet.2026.108906_bib0013","series-title":"11th international conference on learning representations (ICLR)","article-title":"Nagphormer: A tokenized graph transformer for node classification in large graphs","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.108906_bib0014","series-title":"9th international conference on learning representations (ICLR)","article-title":"Adaptive universal generalized pagerank graph neural network","author":"Chien","year":"2021"},{"key":"10.1016\/j.neunet.2026.108906_bib0015","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"Defferrard","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.108906_bib0016","series-title":"3rd international conference on learning representations (ICLR)","article-title":"Adam: A method for stochastic optimization","author":"Diederik","year":"2015"},{"key":"10.1016\/j.neunet.2026.108906_bib0017","series-title":"CoRR","article-title":"A generalization of transformer networks to graphs","author":"Dwivedi","year":"2020"},{"key":"10.1016\/j.neunet.2026.108906_bib0018","series-title":"Orthogonal polynomials: 2nd AIMS-volkswagen stiftung workshop","first-page":"3","article-title":"An introduction to orthogonal polynomials","author":"Foupouagnigni","year":"2020"},{"issue":"23","key":"10.1016\/j.neunet.2026.108906_bib0019","doi-asserted-by":"crossref","first-page":"9679","DOI":"10.1073\/pnas.1019641108","article-title":"Sparse low-order interaction network underlies a highly correlated and learnable neural population code","volume":"108","author":"Ganmor","year":"2011","journal-title":"Proceedings of the National Academy of sciences"},{"key":"10.1016\/j.neunet.2026.108906_bib0020","series-title":"International conference on learning representations (ICLR)","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Gasteiger","year":"2018"},{"key":"10.1016\/j.neunet.2026.108906_bib0021","series-title":"International conference on machine learning","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"Gehring","year":"2017"},{"issue":"7666","key":"10.1016\/j.neunet.2026.108906_bib0022","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1038\/nature23273","article-title":"Higher-order interactions stabilize dynamics in competitive network models","volume":"548","author":"Grilli","year":"2017","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2026.108906_bib0023","first-page":"14239","article-title":"Bernnet: Learning arbitrary graph spectral filters via bernstein approximation","volume":"34","author":"He","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.108906_bib0024","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI)","first-page":"12653","article-title":"Higher-order graph convolutional network with flower-petals laplacians on simplicial complexes","volume":"vol. 38","author":"Huang","year":"2024"},{"key":"10.1016\/j.neunet.2026.108906_bib0025","series-title":"International conference on learning representations","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.neunet.2026.108906_bib0026","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Deeper insights into graph convolutional networks for semi-supervised learning","volume":"vol. 32","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.108906_bib0027","article-title":"Diffusion convolutional recurrent neural network: data-driven traffic forecasting","author":"Li","year":"2018","journal-title":"ICLR"},{"key":"10.1016\/j.neunet.2026.108906_bib0028","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI)","first-page":"506","article-title":"Non-negative matrix factorization with constraints","volume":"vol. 24","author":"Liu","year":"2010"},{"key":"10.1016\/j.neunet.2026.108906_bib0029","series-title":"International conference on machine learning","first-page":"2014","article-title":"Learning convolutional neural networks for graphs","author":"Niepert","year":"2016"},{"key":"10.1016\/j.neunet.2026.108906_bib0030","unstructured":"Pei, H., Wei, B., Chang, K. C., Lei, Y., & Yang, B.. Geom-GCN: Geometric graph convolutional networks. In 8th international conference on learning representations, ICLR 2020, addis ababa, ethiopia, april 26\u201330, 2020."},{"key":"10.1016\/j.neunet.2026.108906_bib0031","series-title":"Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining (KDD)","first-page":"2110","article-title":"Deepinf: Social influence prediction with deep learning","author":"Qiu","year":"2018"},{"issue":"2","key":"10.1016\/j.neunet.2026.108906_bib0032","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1137\/18M1201019","article-title":"Random walks on simplicial complexes and the normalized hodge 1-laplacian","volume":"62","author":"Schaub","year":"2020","journal-title":"SIAM Review"},{"issue":"9","key":"10.1016\/j.neunet.2026.108906_bib0033","article-title":"Weisfeiler-lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108906_bib0034","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.neunet.2026.108906_bib0035","series-title":"8th international conference on learning representations (ICLR)","article-title":"Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","author":"Sun","year":"2020"},{"key":"10.1016\/j.neunet.2026.108906_bib0036","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.108906_bib0037","series-title":"International conference on learning representations (ICLR)","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"10.1016\/j.neunet.2026.108906_bib0038","doi-asserted-by":"crossref","first-page":"2445","DOI":"10.1007\/s00521-018-3748-y","article-title":"Convergence of a modified gradient-based learning algorithm with penalty for single-hidden-layer feed-forward networks","volume":"32","author":"Wang","year":"2018","journal-title":"Neural Computing and Applications"},{"key":"10.1016\/j.neunet.2026.108906_bib0039","series-title":"Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"3164","article-title":"The heterophilic snowflake hypothesis: Training and empowering gnns for heterophilic graphs","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.108906_bib0040","series-title":"International conference on machine learning (ICML)","first-page":"23341","article-title":"How powerful are spectral graph neural networks","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108906_bib0041","series-title":"International conference on machine learning (ICML)","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2026.108906_bib0042","series-title":"International conference on machine learning (ICML)","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","author":"Xu","year":"2018"},{"key":"10.1016\/j.neunet.2026.108906_bib0043","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.108906_bib0044","article-title":"Link prediction based on graph neural networks","volume":"31","author":"Zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.neunet.2026.108906_bib0045","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI)","article-title":"An end-to-end deep learning architecture for graph classification","volume":"vol. 32","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neunet.2026.108906_bib0046","first-page":"7793","article-title":"Beyond homophily in graph neural networks: Current limitations and effective designs","volume":"33","author":"Zhu","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.108906_bib0047","series-title":"Proceedings of the web conference (WWW)","first-page":"1215","article-title":"Interpreting and unifying graph neural networks with an optimization framework","author":"Zhu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108906_bib0048","series-title":"Advanced engineering mathematics","author":"Zill","year":"2020"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003679?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003679?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:50:24Z","timestamp":1781146224000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003679"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":48,"alternative-id":["S0893608026003679"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108906","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond pairwise dependence: A multi-filter fusion network for graph representation learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108906","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108906"}}