{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:05:13Z","timestamp":1784203513464,"version":"3.55.0"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["62403043"],"award-info":[{"award-number":["62403043"]}],"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":["62172023"],"award-info":[{"award-number":["62172023"]}],"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":["62441232"],"award-info":[{"award-number":["62441232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L257022"],"award-info":[{"award-number":["L257022"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007302","name":"Beijing University of Chemical Technology","doi-asserted-by":"publisher","award":["XK2025-06"],"award-info":[{"award-number":["XK2025-06"]}],"id":[{"id":"10.13039\/501100007302","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":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.109025","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T06:52:59Z","timestamp":1776927179000},"page":"109025","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Hybrid graph attention learning with pseudo-label guided adaptive evolution"],"prefix":"10.1016","volume":"202","author":[{"given":"Jinlu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfeng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9803-0256","authenticated-orcid":false,"given":"Junbin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaofan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3096-8261","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yachao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4880-0305","authenticated-orcid":false,"given":"Jipeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109025_bib0001","series-title":"NeurIPS","first-page":"5050","article-title":"Mixmatch: A holistic approach to semi-supervised learning","author":"Berthelot","year":"2019"},{"issue":"4","key":"10.1016\/j.neunet.2026.109025_bib0002","doi-asserted-by":"crossref","first-page":"3279","DOI":"10.1109\/TKDE.2021.3126456","article-title":"A general survey on attention mechanisms in deep learning","volume":"35","author":"Brauwers","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"9","key":"10.1016\/j.neunet.2026.109025_bib0003","doi-asserted-by":"crossref","first-page":"4948","DOI":"10.1109\/TKDE.2025.3586369","article-title":"Adedgedrop: Adversarial edge dropping for robust graph neural networks","volume":"37","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2026.109025_bib0004","series-title":"Aaai","first-page":"4191","article-title":"Dual low-rank graph autoencoder for semantic and topological networks","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109025_bib0005","series-title":"IEEE international conference on acoustics, speech and signal processing (icassp)","first-page":"3897","article-title":"Structured citation trend prediction using graph neural networks","author":"Cummings","year":"2020"},{"key":"10.1016\/j.neunet.2026.109025_bib0006","series-title":"KDD","first-page":"227","article-title":"Nrgnn: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs","author":"Dai","year":"2021"},{"key":"10.1016\/j.neunet.2026.109025_bib0007","series-title":"NeurIPS","first-page":"3837","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"Defferrard","year":"2016"},{"key":"10.1016\/j.neunet.2026.109025_bib0008","series-title":"NeurIPS","first-page":"6790","article-title":"Gemnet: Universal directional graph neural networks for molecules","author":"Gasteiger","year":"2021"},{"key":"10.1016\/j.neunet.2026.109025_bib0009","series-title":"ICLR","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Gasteiger","year":"2019"},{"issue":"6","key":"10.1016\/j.neunet.2026.109025_bib0010","first-page":"1","article-title":"Robust adaptive linear discriminant analysis with bidirectional reconstruction constraint","volume":"14","author":"Guo","year":"2020","journal-title":"ACM Transactions on Knowledge Discovery from Data (TKDD)"},{"issue":"4","key":"10.1016\/j.neunet.2026.109025_bib0011","doi-asserted-by":"crossref","first-page":"2776","DOI":"10.1109\/TII.2020.2986316","article-title":"A deep graph neural network-based mechanism for social recommendations","volume":"17","author":"Guo","year":"2020","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.neunet.2026.109025_bib0012","series-title":"NeurIPS","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017"},{"key":"10.1016\/j.neunet.2026.109025_bib0013","series-title":"KDD","first-page":"802","article-title":"Sgd-dyg: Self-reliant global dependency apprehending on dynamic graphs","author":"Han","year":"2025"},{"key":"10.1016\/j.neunet.2026.109025_bib0014","series-title":"NeurIPS","first-page":"2641","article-title":"Learning conjoint attentions for graph neural nets","author":"He","year":"2021"},{"key":"10.1016\/j.neunet.2026.109025_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117921","article-title":"Graph neural network for traffic forecasting: A survey","volume":"207","author":"Jiang","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109025_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106207","article-title":"A comprehensive survey on deep graph representation learning","volume":"173","author":"Ju","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109025_bib0017","series-title":"ICML","first-page":"10762","article-title":"Simultaneous graph signal clustering and graph learning","author":"Karaaslanli","year":"2022"},{"key":"10.1016\/j.neunet.2026.109025_bib0018","series-title":"ACM CIKM","first-page":"4003","article-title":"S-mixup: Structural mixup for graph neural networks","author":"Kim","year":"2023"},{"key":"10.1016\/j.neunet.2026.109025_bib0019","series-title":"ICLR","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.neunet.2026.109025_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126441","article-title":"A survey of graph neural network based recommendation in social networks","volume":"549","author":"Li","year":"2023","journal-title":"Neurocomputing"},{"issue":"9","key":"10.1016\/j.neunet.2026.109025_bib0021","doi-asserted-by":"crossref","first-page":"8001","DOI":"10.1109\/TPAMI.2025.3572846","article-title":"Multi-channel disentangled graph neural networks with different types of self-constraints","volume":"47","author":"Liang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"10.1016\/j.neunet.2026.109025_bib0022","doi-asserted-by":"crossref","first-page":"2543","DOI":"10.1109\/TNNLS.2022.3145092","article-title":"Deep graph learning for anomalous citation detection","volume":"33","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109025_bib0023","series-title":"AAAI","first-page":"14175","article-title":"NodeMixup: Tackling under-reaching for graph neural networks","author":"Lu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109025_bib0024","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"19143","article-title":"Agmixup: Adaptive graph mixup for semi-supervised node classification","author":"Lu","year":"2025"},{"key":"10.1016\/j.neunet.2026.109025_bib0025","series-title":"KDD","first-page":"701","article-title":"Deepwalk: Online learning of social representations","author":"Perozzi","year":"2014"},{"key":"10.1016\/j.neunet.2026.109025_bib0026","unstructured":"Shchur, O., Mumme, M., Bojchevski, A., & G\u00fcnnemann, S. (2018). Pitfalls of graph neural network evaluation. arXiv: 1811.05868."},{"key":"10.1016\/j.neunet.2026.109025_bib0027","unstructured":"Tang, J., Hu, W., Gao, X., & Guo, Z. (2019). Joint learning of graph representation and node features in graph convolutional neural networks. arXiv: 1909.04931."},{"key":"10.1016\/j.neunet.2026.109025_bib0028","first-page":"1","article-title":"Chebnet: Efficient and stable constructions of deep neural networks with rectified power units via chebyshev approximation","author":"Tang","year":"2024","journal-title":"Communications in Mathematics and Statistics"},{"key":"10.1016\/j.neunet.2026.109025_bib0029","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/978-3-319-60801-3_27","article-title":"Multilayer perceptron (MLP)","author":"Taud","year":"2018","journal-title":"Geomatic Approaches for Modeling Land Change Scenarios"},{"key":"10.1016\/j.neunet.2026.109025_bib0030","series-title":"ICLR","article-title":"Graph attention networks","author":"Velickovic","year":"2018"},{"key":"10.1016\/j.neunet.2026.109025_bib0031","series-title":"AAAI","first-page":"10024","article-title":"Graphmix: Improved training of gnns for semi-supervised learning","author":"Verma","year":"2021"},{"issue":"10","key":"10.1016\/j.neunet.2026.109025_bib0032","doi-asserted-by":"crossref","first-page":"2165","DOI":"10.1109\/JAS.2024.124863","article-title":"GT-A2T: Graph tensor alliance attention network","volume":"12","author":"Wang","year":"2025","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"10.1016\/j.neunet.2026.109025_bib0033","article-title":"Capturing local and global information: Multi-view graph convolutional network via granular-ball computing and collaborative matrix","volume":"296","author":"Wang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109025_bib0034","series-title":"NeurIPS","first-page":"137698","article-title":"Graph classification via reference distribution learning: Theory and practice","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109025_bib0035","series-title":"ICML","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"issue":"2","key":"10.1016\/j.neunet.2026.109025_bib0036","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1561\/2200000096","article-title":"Graph neural networks for natural language processing: A survey","volume":"16","author":"Wu","year":"2023","journal-title":"Foundations and Trends in Machine Learning"},{"issue":"1","key":"10.1016\/j.neunet.2026.109025_bib0037","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"6","key":"10.1016\/j.neunet.2026.109025_bib0038","doi-asserted-by":"crossref","first-page":"2450","DOI":"10.1109\/TCBBIO.2025.3593469","article-title":"A hybrid ensemble end-to-end neural network for accurate protein-protein interactions prediction","volume":"22","author":"Yang","year":"2025","journal-title":"IEEE Transactions on Computational Biology and Bioinformatics"},{"issue":"6","key":"10.1016\/j.neunet.2026.109025_bib0039","doi-asserted-by":"crossref","first-page":"2518","DOI":"10.1109\/TCBB.2024.3486216","article-title":"An end-to-end knowledge graph fused graph neural network for accurate protein-protein interactions prediction","volume":"21","author":"Yang","year":"2024","journal-title":"IEEE\/ACM Transactions on Computational Biology and Bioinformatics"},{"key":"10.1016\/j.neunet.2026.109025_bib0040","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.neunet.2022.11.027","article-title":"Multi-graph fusion graph convolutional networks with pseudo-label supervision","volume":"158","author":"Yang","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109025_bib0041","series-title":"Icml","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","author":"Yang","year":"2016"},{"issue":"6","key":"10.1016\/j.neunet.2026.109025_bib0042","doi-asserted-by":"crossref","first-page":"11507","DOI":"10.1109\/TNNLS.2024.3514652","article-title":"A node-collaboration-informed graph convolutional network for highly accurate representation to undirected weighted graph","volume":"36","author":"Yuan","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109025_bib0043","series-title":"AAAI","first-page":"16750","article-title":"Hongat: Graph attention networks in the presence of high-order neighbors","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109025_bib0044","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2023.09.042","article-title":"Beyond low-pass filtering on large-scale graphs via adaptive filtering graph neural networks","volume":"169","author":"Zhang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109025_bib0045","series-title":"KDD","first-page":"2515","article-title":"Improving social network embedding via new second-order continuous graph neural networks","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109025_bib0046","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.neunet.2022.09.017","article-title":"Adaptive graph convolutional clustering network with optimal probabilistic graph","volume":"156","author":"Zhao","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109025_bib0047","series-title":"2022 International joint conference on neural networks (IJCNN)","first-page":"1","article-title":"Robust graph convolutional clustering with adaptive graph learning","author":"Zhao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109025_bib0048","article-title":"Dual-level noise augmentation for graph clustering with triplet-wise contrastive learning","volume":"172","author":"Zhao","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109025_bib0049","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.aiopen.2022.11.006","article-title":"On the distribution alignment of propagation in graph neural networks","volume":"3","author":"Zheng","year":"2022","journal-title":"AI Open"},{"issue":"1","key":"10.1016\/j.neunet.2026.109025_bib0050","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1109\/TBDATA.2022.3156366","article-title":"Dstagcn: Dynamic spatial-temporal adjacent graph convolutional network for traffic forecasting","volume":"9","author":"Zheng","year":"2023","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.neunet.2026.109025_bib0051","series-title":"NeurIPS","first-page":"75095","article-title":"Intramix: Intra-class mixup generation for accurate labels and neighbors","author":"Zheng","year":"2024"},{"issue":"8","key":"10.1016\/j.neunet.2026.109025_bib0052","doi-asserted-by":"crossref","first-page":"3751","DOI":"10.1109\/TKDE.2024.3363703","article-title":"Differentiable clustering for graph attention","volume":"36","author":"Zhou","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2026.109025_bib0053","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"issue":"2","key":"10.1016\/j.neunet.2026.109025_bib0054","first-page":"12","article-title":"Heterophily and graph neural networks: Past, present and future","volume":"46","author":"Zhu","year":"2023","journal-title":"IEEE Data Engineering Bulletin"},{"issue":"14","key":"10.1016\/j.neunet.2026.109025_bib0055","doi-asserted-by":"crossref","first-page":"i190","DOI":"10.1093\/bioinformatics\/btx252","article-title":"Predicting multicellular function through multi-layer tissue networks","volume":"33","author":"Zitnik","year":"2017","journal-title":"Bioinformatics"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004855?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004855?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:17:44Z","timestamp":1784200664000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004855"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":55,"alternative-id":["S0893608026004855"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109025","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hybrid graph attention learning with pseudo-label guided adaptive evolution","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109025","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":"109025"}}