{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:11:40Z","timestamp":1778271100665,"version":"3.51.4"},"reference-count":47,"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":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010882","name":"Tianjin Municipal Education Commission","doi-asserted-by":"publisher","award":["2023KJ277"],"award-info":[{"award-number":["2023KJ277"]}],"id":[{"id":"10.13039\/501100010882","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3304503"],"award-info":[{"award-number":["2023YFC3304503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402337"],"award-info":[{"award-number":["62402337"]}],"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":["62372323,92370111"],"award-info":[{"award-number":["62372323,92370111"]}],"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":["62276187"],"award-info":[{"award-number":["62276187"]}],"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":["62422210"],"award-info":[{"award-number":["62422210"]}],"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":["62272340"],"award-info":[{"award-number":["62272340"]}],"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":["92370111"],"award-info":[{"award-number":["92370111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.ins.2026.123437","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T03:40:44Z","timestamp":1774928444000},"page":"123437","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Unifying heterophily and oversmoothing in graph neural networks via feature spectral diversity"],"prefix":"10.1016","volume":"746","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6122-6482","authenticated-orcid":false,"given":"Renbiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123437_bib0005","series-title":"International Conference on Learning Representations","article-title":"Semi-Supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.ins.2026.123437_bib0010","series-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"639","article-title":"LightGCN: simplifying and powering graph convolution network for recommendation","author":"He","year":"2020"},{"key":"10.1016\/j.ins.2026.123437_bib0015","doi-asserted-by":"crossref","DOI":"10.1002\/asia.202200269","article-title":"MolNet: a chemically intuitive graph neural network for prediction of molecular properties","volume":"17","author":"Kim","year":"2022","journal-title":"Chem. Asian J."},{"key":"10.1016\/j.ins.2026.123437_bib0020","series-title":"International Conference on Learning Representations","article-title":"Graph attention networks","author":"Velickovic","year":"2018"},{"key":"10.1016\/j.ins.2026.123437_bib0025","series-title":"Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS-16)","first-page":"3837","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"Defferrard","year":"2016"},{"key":"10.1016\/j.ins.2026.123437_bib0030","series-title":"Proceedings of the 34th Conference on Neural Information Processing Systems","first-page":"7793","article-title":"Beyond homophily in graph neural networks: current limitations and effective designs","author":"Zhu","year":"2020"},{"key":"10.1016\/j.ins.2026.123437_bib0035","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","author":"Li","year":"2018"},{"key":"10.1016\/j.ins.2026.123437_bib0040","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"18960","article-title":"Integrating co-training with edge discrimination to enhance graph neural networks under heterophily","volume":"vol. 39","author":"Liu","year":"2025"},{"key":"10.1016\/j.ins.2026.123437_bib0045","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3438","article-title":"Measuring and relieving the Over-Smoothing problem for graph neural networks from the topological view","author":"Chen","year":"2020"},{"key":"10.1016\/j.ins.2026.123437_bib0050","series-title":"Proceedings of the 36th Neural Information Processing Systems","first-page":"1362","article-title":"Revisiting heterophily for graph neural networks","author":"Luan","year":"2022"},{"key":"10.1016\/j.ins.2026.123437_bib0055","series-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)","first-page":"338","article-title":"Towards deeper graph neural networks","author":"Liu","year":"2020"},{"key":"10.1016\/j.ins.2026.123437_bib0060","series-title":"Proceedings of the 2022 IEEE International Conference on Data Mining","first-page":"1287","article-title":"Two sides of the same coin: heterophily and oversmoothing in graph convolutional neural networks","author":"Yan","year":"2022"},{"key":"10.1016\/j.ins.2026.123437_bib0065","series-title":"Proceedings of the 41st International Conference on Machine Learning","first-page":"40078","article-title":"Multi-Track message passing: tackling oversmoothing and oversquashing in graph learning via preventing heterophily mixing","volume":"vol. 235","author":"Pei","year":"2024"},{"key":"10.1016\/j.ins.2026.123437_bib0070","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3950","article-title":"Beyond Low-Frequency information in graph convolutional networks","author":"Bo","year":"2021"},{"key":"10.1016\/j.ins.2026.123437_bib0075","series-title":"International Conference on Learning Representations","article-title":"Adaptive universal generalized PageRank graph neural network","author":"Chien","year":"2021"},{"key":"10.1016\/j.ins.2026.123437_bib0080","series-title":"Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS)","first-page":"14239","article-title":"BernNet: learning arbitrary graph spectral filters via bernstein approximation","author":"He","year":"2021"},{"key":"10.1016\/j.ins.2026.123437_bib0085","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"23341","article-title":"How powerful are spectral graph neural networks","author":"Wang","year":"2022"},{"key":"10.1016\/j.ins.2026.123437_bib0090","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"13437","article-title":"PC-CONV: unifying homophily and heterophily with two-fold filtering","author":"Li","year":"2024"},{"key":"10.1016\/j.ins.2026.123437_bib0095","series-title":"Proceedings of the 41st International Conference on Machine Learning","article-title":"How universal polynomial bases enhance spectral graph neural networks: heterophily, over-smoothing, and oversquashing","author":"Huang","year":"2024"},{"key":"10.1016\/j.ins.2026.123437_bib0100","series-title":"Proceedings of the 38th Neural Information Processing Systems","first-page":"93540","article-title":"Unifying homophily and heterophily for spectral graph neural networks via triple filter ensembles","author":"Duan","year":"2024"},{"key":"10.1016\/j.ins.2026.123437_bib0105","article-title":"Adp-gnn: a spectral graph neural network framework unifying homophilic and heterophilic patterns via adaptive dual-polynomial filters","author":"Zhu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.ins.2026.123437_bib0110","series-title":"Proceedings of the ACM Web Conference 2024","first-page":"803","article-title":"Cross-space adaptive filter: integrating graph topology and node attributes for alleviating the over-smoothing problem","author":"Huang","year":"2024"},{"key":"10.1016\/j.ins.2026.123437_bib0115","author":"Hevapathige"},{"key":"10.1016\/j.ins.2026.123437_bib0120","author":"Shirzadi"},{"key":"10.1016\/j.ins.2026.123437_bib0125","series-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining v. 2","first-page":"944","article-title":"Depth-adaptive graph neural networks via learnable bakry-\u00e9mery curvature","author":"Hevapathige","year":"2025"},{"key":"10.1016\/j.ins.2026.123437_bib0130","author":"Luan"},{"key":"10.1016\/j.ins.2026.123437_bib0135","series-title":"International Conference on Learning Representations","article-title":"Graph neural networks exponentially lose expressive power for node classification","author":"Oono","year":"2020"},{"key":"10.1016\/j.ins.2026.123437_bib0140","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.1016\/j.ins.2026.123437_bib0145","series-title":"Proceedings of the 40th International Conference on Machine Learning","first-page":"18774","article-title":"Towards deep attention in graph neural networks: problems and remedies","author":"Lee","year":"2023"},{"key":"10.1016\/j.ins.2026.123437_bib0150","series-title":"Proceedings of the 8th International Conference on Learning Representations","article-title":"Geom-GCN: geometric graph convolutional networks","author":"Pei","year":"2020"},{"key":"10.1016\/j.ins.2026.123437_bib0155","series-title":"Proceedings of the Web Conference 2021","first-page":"1215","article-title":"Interpreting and unifying graph neural networks with an optimization framework","author":"Zhu","year":"2021"},{"key":"10.1016\/j.ins.2026.123437_bib0160","series-title":"Proceedings of the ACM Web Conference 2023","first-page":"306","article-title":"Graph neural networks with diverse spectral filtering","author":"Guo","year":"2023"},{"key":"10.1016\/j.ins.2026.123437_bib0165","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/BF00327297","article-title":"The emergence of the weierstrassian approach to complex analysis","volume":"14","author":"Manning","year":"1975","journal-title":"Arch. Hist. Exact Sci."},{"key":"10.1016\/j.ins.2026.123437_bib0170","series-title":"Proceedings of the 30th International Joint Conference on Artificial Intelligence","first-page":"2515","article-title":"Masked label prediction: unified message passing model for Semi-Supervised classification","author":"Shi","year":"2021"},{"key":"10.1016\/j.ins.2026.123437_bib0175","series-title":"Proceedings of the 33rd International Conference on Machine Learning","first-page":"40","article-title":"Revisiting Semi-Supervised learning with graph embeddings","volume":"vol. 48","author":"Yang","year":"2016"},{"key":"10.1016\/j.ins.2026.123437_bib0180","series-title":"Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"807","article-title":"Social influence analysis in Large-Scale networks","author":"Tang","year":"2009"},{"key":"10.1016\/j.ins.2026.123437_bib0185","series-title":"Advances in Neural Information Processing Systems","first-page":"20887","article-title":"Large scale learning on Non-Homophilous graphs: new benchmarks and strong simple methods","volume":"vol. 34","author":"Lim","year":"2021"},{"key":"10.1016\/j.ins.2026.123437_bib0190","doi-asserted-by":"crossref","first-page":"7264","DOI":"10.52202\/068431-0527","article-title":"Convolutional neural networks on graphs with Chebyshev approximation, revisited","volume":"35","author":"He","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123437_bib0195","series-title":"Proceedings of the ACM on Web Conference","first-page":"3160","article-title":"Iceberg: debiased Self-Training for Class-Imbalanced node classification","author":"Li","year":"2025"},{"key":"10.1016\/j.ins.2026.123437_bib0200","series-title":"International Conference on Learning Representations","article-title":"Predict then propagate: graph neural networks meet personalized PageRank","author":"Gasteiger","year":"2019"},{"key":"10.1016\/j.ins.2026.123437_bib0205","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"1725","article-title":"Simple and deep graph convolutional networks","author":"Chen","year":"2020"},{"key":"10.1016\/j.ins.2026.123437_bib0210","series-title":"International Conference on Learning Representations","article-title":"Anti-Symmetric DGN: a stable architecture for deep graph networks","author":"Gravina","year":"2023"},{"key":"10.1016\/j.ins.2026.123437_bib0215","series-title":"Proceedings of the 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.ins.2026.123437_bib0220","series-title":"Proceedings of the 35th Conference on Neural Information Processing Systems","first-page":"4751","article-title":"Diverse message passing for attribute with heterophily","author":"Yang","year":"2021"},{"key":"10.1016\/j.ins.2026.123437_bib0225","series-title":"International Conference on Learning Representations","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.ins.2026.123437_bib0230","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9267","article-title":"DeepGCNs: can GCNs go as deep as CNNs?","author":"Li","year":"2019"},{"key":"10.1016\/j.ins.2026.123437_bib0235","series-title":"International Conference on Learning Representations","article-title":"Ordered GNN: ordering message passing to deal with heterophily and over-smoothing","author":"Song","year":"2023"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526003683?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526003683?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:11:33Z","timestamp":1778267493000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526003683"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":47,"alternative-id":["S0020025526003683"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123437","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Unifying heterophily and oversmoothing in graph neural networks via feature spectral diversity","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123437","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123437"}}