{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T16:12:09Z","timestamp":1778515929122,"version":"3.51.4"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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","award":["62572420"],"award-info":[{"award-number":["62572420"]}],"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":["62273290"],"award-info":[{"award-number":["62273290"]}],"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":["61572419"],"award-info":[{"award-number":["61572419"]}],"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":[[2026,3]]},"DOI":"10.1016\/j.neunet.2025.108287","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T16:48:41Z","timestamp":1762274921000},"page":"108287","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Multi-spectral attention and graph smoothness enhancement for generalized node classification"],"prefix":"10.1016","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3076-8885","authenticated-orcid":false,"given":"Xinghai","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5388-6920","authenticated-orcid":false,"given":"Jinglei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108287_bib0001","series-title":"International conference on machine learning","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.2025.108287_bib0002","series-title":"The eleventh international conference on learning representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","first-page":"1","article-title":"Specformer: Spectral graph neural networks meet transformers","author":"Bo","year":"2023"},{"key":"10.1016\/j.neunet.2025.108287_bib0003","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3950","article-title":"Beyond low-frequency information in graph convolutional networks","volume":"vol. 35","author":"Bo","year":"2021"},{"key":"10.1016\/j.neunet.2025.108287_bib0004","series-title":"Conf. on learning representations, ICLR 2014-conference track proceedings","first-page":"1","article-title":"Spectral networks and deep locally connected networks on graphs, 2nd int","author":"Bruna","year":"2014"},{"key":"10.1016\/j.neunet.2025.108287_bib0005","series-title":"Proceedings of the 38th international conference on machine learning","first-page":"1407","article-title":"GRAND: Graph neural diffusion","volume":"vol. 139","author":"Chamberlain","year":"2021"},{"key":"10.1016\/j.neunet.2025.108287_bib0006","doi-asserted-by":"crossref","first-page":"27184","DOI":"10.52202\/068431-1971","article-title":"Simplified graph convolution with heterophily","volume":"35","author":"Chanpuriya","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108287_bib0007","series-title":"Proceedings of the 37th international conference on machine learning, ICML 2020","first-page":"1673","article-title":"Simple and deep graph convolutional networks","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2025.108287_bib0008","series-title":"9th International conference on learning representations, ICLR 2021, virtual event, Austria, May 3-7, 2021","first-page":"1","article-title":"Adaptive universal generalized pagerank graph neural network","author":"Chien","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2025.108287_bib0009","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/s43586-024-00294-7","article-title":"Graph neural networks","volume":"4","author":"Corso","year":"2024","journal-title":"Nature Reviews Methods Primers"},{"issue":"4","key":"10.1016\/j.neunet.2025.108287_bib0010","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF02551274","article-title":"Approximation by superpositions of a sigmoidal function","volume":"2","author":"Cybenko","year":"1989","journal-title":"Mathematics of Control, Signals and Systems"},{"key":"10.1016\/j.neunet.2025.108287_bib0011","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"},{"key":"10.1016\/j.neunet.2025.108287_bib0012","unstructured":"Deng, G., Zhou, H., Kannan, R., & Prasanna, V. (2025). Mixture of scope experts at test: Generalizing deeper graph neural networks with shallow variants. https:\/\/arxiv.org\/abs\/2409.06998."},{"key":"10.1016\/j.neunet.2025.108287_bib0013","first-page":"1","article-title":"Adaptive homophily clustering: Structure homophily graph learning with adaptive filter for hyperspectral image","volume":"63","author":"Ding","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.108287_bib0014","doi-asserted-by":"crossref","unstructured":"Ding, Y., Zhang, Z., Yang, A., Cai, Y., Xiao, X., Hong, D., & Yuan, J. (2025b). SLCGC: A lightweight self-supervised low-pass contrastive graph clustering network for hyperspectral images. https:\/\/arxiv.org\/abs\/2502.03497.","DOI":"10.1109\/TMM.2025.3604954"},{"key":"10.1016\/j.neunet.2025.108287_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119858","article-title":"Multi-scale receptive fields: Graph attention neural network for hyperspectral image classification","volume":"223","author":"Ding","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2025.108287_bib0016","series-title":"The tenth international conference on learning representations, ICLR","first-page":"1","article-title":"Graph neural networks with learnable structural and positional representations","author":"Dwivedi","year":"2022"},{"key":"10.1016\/j.neunet.2025.108287_bib0017","series-title":"2013 IEEE 29th international conference on data engineering (ICDE)","first-page":"613","article-title":"RoundTripRank: Graph-based proximity with importance and specificity?","author":"Fang","year":"2013"},{"key":"10.1016\/j.neunet.2025.108287_bib0018","series-title":"International conference on machine learning ICML","first-page":"12077","article-title":"Graph neural networks with learnable and optimal polynomial bases","volume":"vol. 202","author":"Guo","year":"2023"},{"key":"10.1016\/j.neunet.2025.108287_bib0019","series-title":"Advances in neural information processing systems 34: Annual conference on neural information processing systems 2021, NeurIPS 2021, December 6-14, 2021, virtual","first-page":"14239","article-title":"BernNet: Learning arbitrary graph spectral filters via bernstein approximation","author":"He","year":"2021"},{"key":"10.1016\/j.neunet.2025.108287_bib0020","series-title":"Advances in neural information processing systems","first-page":"32095","article-title":"Convolutional neural networks on graphs with Chebyshev approximation, revisited","volume":"vol. 35","author":"He","year":"2022"},{"issue":"5","key":"10.1016\/j.neunet.2025.108287_bib0021","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108287_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113615","article-title":"Mitigating over-smoothing in graph neural networks for node classification through adaptive early embedding and biased dropedge procedures","volume":"320","author":"Hoseinnia","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2025.108287_bib0023","series-title":"Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"594-604","article-title":"GraphMAE: Self-supervised masked graph autoencoders","author":"Hou","year":"2022"},{"key":"10.1016\/j.neunet.2025.108287_bib0024","series-title":"Proceedings of the ACM on web conference 2024, WWW","first-page":"1057","article-title":"Optimizing polynomial graph filters: A novel adaptive Krylov subspace approach","author":"Huang","year":"2024"},{"key":"10.1016\/j.neunet.2025.108287_bib0025","series-title":"Forty-first international conference on machine learning, ICML 2024, Vienna, Austria, July 21-27, 2024","first-page":"21199","article-title":"How universal polynomial bases enhance spectral graph neural networks: Heterophily, over-smoothing, and over-squashing","volume":"vol. 235","author":"Huang","year":"2024"},{"key":"10.1016\/j.neunet.2025.108287_bib0026","series-title":"Database systems for advanced applications","first-page":"342","article-title":"H2GNN: Graph neural networks with homophilic and heterophilic feature aggregations","author":"Jing","year":"2024"},{"key":"10.1016\/j.neunet.2025.108287_bib0027","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.neunet.2025.108287_bib0028","series-title":"7th International conference on learning representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019","first-page":"1","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Klicpera","year":"2019"},{"key":"10.1016\/j.neunet.2025.108287_bib0029","series-title":"Advances in neural information processing systems","first-page":"2977","article-title":"EvenNet: Ignoring odd-hop neighbors improves robustness of graph neural networks","volume":"vol. 35","author":"Lei","year":"2022"},{"key":"10.1016\/j.neunet.2025.108287_bib0030","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3538","article-title":"Deeper insights into graph convolutional networks for semi-supervised learning","volume":"vol. 32","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2025.108287_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106285","article-title":"A novel interactive deep cascade spectral graph convolutional network with multi-relational graphs for disease prediction","volume":"175","author":"Li","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108287_bib0032","series-title":"International conference on machine learning, ICML 2022","first-page":"13242","article-title":"Finding global homophily in graph neural networks when meeting heterophily","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2025.108287_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106933","article-title":"CDCGAN: Class distribution-aware conditional gan-based minority augmentation for imbalanced node classification","volume":"183","author":"Liu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108287_bib0034","doi-asserted-by":"crossref","first-page":"194804","DOI":"10.1109\/ACCESS.2024.3520903","article-title":"Information-enhanced graph neural network for transcending homophily barriers","volume":"12","author":"Liu","year":"2024","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.neunet.2025.108287_bib0035","first-page":"784","article-title":"Neighbor-anchoring adversarial graph neural networks","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2025.108287_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.epsr.2025.111525","article-title":"MSGCN: Multi-task spectral graph convolutional model for identification of branch parameters considered grid topology","volume":"243","author":"Liu","year":"2025","journal-title":"Electric Power Systems Research"},{"key":"10.1016\/j.neunet.2025.108287_bib0037","series-title":"The tenth international conference on learning representations, ICLR 2022, virtual event, April 25-29, 2022","first-page":"1","article-title":"Is homophily a necessity for graph neural networks?","author":"Ma","year":"2022"},{"key":"10.1016\/j.neunet.2025.108287_bib0038","article-title":"Piecewise constant spectral graph neural network","volume":"2025","author":"Martirosyan","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2025.108287_bib0039","series-title":"8th International conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020","first-page":"1","article-title":"Graph neural networks exponentially lose expressive power for node classification","author":"Oono","year":"2020"},{"key":"10.1016\/j.neunet.2025.108287_bib0040","series-title":"International joint conference on artificial intelligence","first-page":"2609","article-title":"Adversarially regularized graph autoencoder for graph embedding","author":"Pan","year":"2018"},{"key":"10.1016\/j.neunet.2025.108287_bib0041","series-title":"8th International conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020","first-page":"1","article-title":"Geom-GCN: Geometric graph convolutional networks","author":"Pei","year":"2020"},{"key":"10.1016\/j.neunet.2025.108287_bib0042","series-title":"Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining","first-page":"701","article-title":"DeepWalk: Online learning of social representations","author":"Perozzi","year":"2014"},{"issue":"3","key":"10.1016\/j.neunet.2025.108287_bib0043","article-title":"Collective classification in network data","volume":"29","author":"Prithviraj","year":"2008","journal-title":"AI Magazine"},{"key":"10.1016\/j.neunet.2025.108287_bib0044","unstructured":"Rong, Y., Huang, W., Xu, T., & Huang, J. (2019). DropEdge: Towards deep graph convolutional networks on node classification. arXiv preprint arXiv: 1907.10903."},{"key":"10.1016\/j.neunet.2025.108287_bib0045","article-title":"SIGN: Scalable inception graph neural networks","volume":"abs\/2004.11198","author":"Rossi","year":"2020","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2025.108287_bib0046","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"10.1016\/j.neunet.2025.108287_bib0047","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2508","article-title":"GraphGAN: Graph representation learning with generative adversarial nets","volume":"vol. 32","author":"Wang","year":"2018"},{"key":"10.1016\/j.neunet.2025.108287_bib0048","series-title":"International conference on machine learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA","first-page":"23341","article-title":"How powerful are spectral graph neural networks","volume":"vol. 162","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108287_bib0049","series-title":"International conference on machine learning","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"issue":"6","key":"10.1016\/j.neunet.2025.108287_bib0050","doi-asserted-by":"crossref","first-page":"7216","DOI":"10.1007\/s10489-022-03836-2","article-title":"QPGCN: Graph convolutional network with a quadratic polynomial filter for overcoming over-smoothing","volume":"53","author":"Wu","year":"2023","journal-title":"Applied Intelligence"},{"issue":"5","key":"10.1016\/j.neunet.2025.108287_bib0051","doi-asserted-by":"crossref","first-page":"8085","DOI":"10.1109\/TNNLS.2024.3438835","article-title":"SAGN: Sparse adaptive gated graph neural network with graph regularization for identifying dual-view brain networks","volume":"36","author":"Xue","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.108287_bib0052","article-title":"From trainable negative depth to edge heterophily in graphs","volume":"36","author":"Yan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108287_bib0053","series-title":"Proceedings of the ACM on web conference 2024","first-page":"2485","article-title":"PaCEr: Network embedding from positional to structural","author":"Yan","year":"2024"},{"key":"10.1016\/j.neunet.2025.108287_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2023.12.037","article-title":"Local structure-aware graph contrastive representation learning","volume":"172","author":"Yang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108287_bib0055","series-title":"2023 IEEE International symposium on high-performance computer architecture (HPCA)","first-page":"1","article-title":"SGCN: Exploiting compressed-sparse features in deep graph convolutional network accelerators","author":"Yoo","year":"2023"},{"issue":"6","key":"10.1016\/j.neunet.2025.108287_bib0056","first-page":"1","article-title":"Building shortcuts between distant nodes with biaffine mapping for graph convolutional networks","volume":"18","author":"Zhang","year":"2024","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"10.1016\/j.neunet.2025.108287_bib0057","series-title":"IJCAI","first-page":"3737","article-title":"Hierarchical diffusion scattering graph neural network","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108287_bib0058","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106228","article-title":"DWSSA: Alleviating over-smoothness for deep graph neural networks","volume":"174","author":"Zhang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108287_bib0059","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106931","article-title":"Graph batch coarsening framework for scalable graph neural networks","volume":"183","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108287_bib0060","series-title":"Advances in neural information processing systems","first-page":"68211","article-title":"Deep graph neural networks via posteriori-sampling-based node-adaptative residual module","volume":"vol. 37","author":"Zhou","year":"2024"},{"key":"10.1016\/j.neunet.2025.108287_bib0061","first-page":"4917","article-title":"Towards deeper graph neural networks with differentiable group normalization","volume":"33","author":"Zhou","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108287_bib0062","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"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011682?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011682?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T15:33:50Z","timestamp":1778513630000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025011682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":62,"alternative-id":["S0893608025011682"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108287","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-spectral attention and graph smoothness enhancement for generalized node classification","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108287","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108287"}}