{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T08:07:05Z","timestamp":1789200425640,"version":"build-2803163510"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["62507035"],"award-info":[{"award-number":["62507035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.asoc.2026.116254","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T15:48:47Z","timestamp":1787068127000},"page":"116254","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Dual token mixing-based graph transformer for semi-supervised node classification in attributed networks"],"prefix":"10.1016","volume":"203","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7588-6713","authenticated-orcid":false,"given":"Jinsong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3387-6118","authenticated-orcid":false,"given":"Mingwen","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2902-7365","authenticated-orcid":false,"given":"Duantengchuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.116254_bib0005","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.asoc.2026.116254_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106919","article-title":"Rethinking the impact of noisy labels in graph classification: a utility and privacy perspective","volume":"182","author":"Li","year":"2025","journal-title":"Neural Netw."},{"issue":"9","key":"10.1016\/j.asoc.2026.116254_bib0015","doi-asserted-by":"crossref","first-page":"7955","DOI":"10.1007\/s10115-025-02473-8","article-title":"Hybrid long-range dependency-aware graph convolutional network for node classification","volume":"67","author":"Chen","year":"2025","journal-title":"Knowl. Inf. Syst."},{"key":"10.1016\/j.asoc.2026.116254_bib0020","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"10.1016\/j.asoc.2026.116254_bib0025","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"6938","article-title":"FedRog: robust federated graph classification for strong heterogeneity and high-noise scenarios","author":"Li","year":"2025"},{"key":"10.1016\/j.asoc.2026.116254_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106113","article-title":"Contrastive learning of graphs under label noise","volume":"172","author":"Li","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.asoc.2026.116254_bib0035","series-title":"Proceedings of the Forty-Second International Conference on Machine Learning","article-title":"Enhancing the influence of labels on unlabeled nodes in graph convolutional networks","author":"Huang","year":"2025"},{"key":"10.1016\/j.asoc.2026.116254_bib0040","series-title":"Proceedings of the Forty-First International Conference on Machine Learning","article-title":"On which nodes does GCN fail? Enhancing GCN from the node perspective","author":"Huang","year":"2024"},{"key":"10.1016\/j.asoc.2026.116254_bib0045","series-title":"Proceedings of the IEEE International Conference on Data Mining","article-title":"Structural robust label propagation on homogeneous graphs","author":"He","year":"2022"},{"issue":"5","key":"10.1016\/j.asoc.2026.116254_bib0050","doi-asserted-by":"crossref","first-page":"5973","DOI":"10.1109\/TCSS.2024.3387487","article-title":"PAMT: a novel propagation-based approach via adaptive similarity mask for node classification","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"issue":"4","key":"10.1016\/j.asoc.2026.116254_bib0055","first-page":"1","article-title":"Bayesian graph local extrema convolution with long-tail strategy for misinformation detection","volume":"18","author":"Zhang","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data"},{"issue":"6","key":"10.1016\/j.asoc.2026.116254_bib0060","first-page":"1","article-title":"Mitigating propensity bias of large language models for recommender systems","volume":"43","author":"Zhang","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.asoc.2026.116254_bib0065","series-title":"Proceedings of the Forty-Second International Conference on Machine Learning","article-title":"Do we really need message passing in brain network modeling?","author":"Yang","year":"2025"},{"issue":"3","key":"10.1016\/j.asoc.2026.116254_bib0070","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1109\/JAS.2025.125336","article-title":"Modularized graph convolutional network","volume":"13","author":"He","year":"2026","journal-title":"IEEE CAA J. Autom. Sinica"},{"key":"10.1016\/j.asoc.2026.116254_bib0075","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","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.asoc.2026.116254_bib0080","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"On the bottleneck of graph neural networks and its practical implications","author":"Alon","year":"2021"},{"key":"10.1016\/j.asoc.2026.116254_bib0085","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","first-page":"28877","article-title":"Do transformers really perform badly for graph representation","author":"Ying","year":"2021"},{"key":"10.1016\/j.asoc.2026.116254_bib0090","series-title":"Proceedings of the 38th Annual Conference on Neural Information Processing Systems","article-title":"Leveraging contrastive learning for enhanced node representations in tokenized graph transformers","author":"Chen","year":"2024"},{"issue":"2","key":"10.1016\/j.asoc.2026.116254_bib0095","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TBDATA.2025.3624955","article-title":"NTFormer: a composite node tokenized graph transformer for node classification","volume":"12","author":"Chen","year":"2026","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.asoc.2026.116254_bib0100","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.asoc.2026.116254_bib0105","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","first-page":"13266","article-title":"Representing long-range context for graph neural networks with global attention","author":"Jain","year":"2021"},{"key":"10.1016\/j.asoc.2026.116254_bib0110","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","article-title":"Recipe for a general, powerful, scalable graph transformer","author":"Ramp\u00e1\u0161ek","year":"2022"},{"key":"10.1016\/j.asoc.2026.116254_bib0115","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"NAGphormer: a tokenized graph transformer for node classification in large graphs","author":"Chen","year":"2023"},{"key":"10.1016\/j.asoc.2026.116254_bib0120","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","article-title":"Simplifying and empowering transformers for large-graph representations","author":"Wu","year":"2023"},{"key":"10.1016\/j.asoc.2026.116254_bib0125","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","article-title":"Hierarchical graph transformer with adaptive node sampling","author":"Zhang","year":"2022"},{"key":"10.1016\/j.asoc.2026.116254_bib0130","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Adaptive universal generalized pagerank graph neural network","author":"Chien","year":"2021"},{"key":"10.1016\/j.asoc.2026.116254_bib0135","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Specformer: spectral graph neural networks meet transformers","author":"Bo","year":"2023"},{"key":"10.1016\/j.asoc.2026.116254_bib0140","series-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"2118","article-title":"PolyFormer: scalable node-wise filters via polynomial graph transformer","author":"Ma","year":"2024"},{"key":"10.1016\/j.asoc.2026.116254_bib0145","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"54656","article-title":"Less is more: on the over-globalizing problem in graph transformers","author":"Xing","year":"2024"},{"key":"10.1016\/j.asoc.2026.116254_bib0150","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Predict then propagate: graph neural networks meet personalized PageRank","author":"Klicpera","year":"2019"},{"key":"10.1016\/j.asoc.2026.116254_bib0155","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"How attentive are graph attention networks?","author":"Brody","year":"2022"},{"key":"10.1016\/j.asoc.2026.116254_bib0160","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","first-page":"2641","article-title":"Learning conjoint attentions for graph neural nets","author":"He","year":"2021"},{"key":"10.1016\/j.asoc.2026.116254_bib0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2024.104129","article-title":"Polarized message-passing in graph neural networks","volume":"331","author":"He","year":"2024","journal-title":"Artif. Intell."},{"issue":"8","key":"10.1016\/j.asoc.2026.116254_bib0170","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 Trans. Knowl. Data Eng."},{"key":"10.1016\/j.asoc.2026.116254_bib0175","series-title":"Proceedings of the International Conference on Machine Learning","article-title":"Simple and deep graph convolutional networks","author":"Chen","year":"2020"},{"key":"10.1016\/j.asoc.2026.116254_bib0180","series-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"1243","article-title":"AM-GCN: adaptive multi-channel graph convolutional networks","author":"Wang","year":"2020"},{"key":"10.1016\/j.asoc.2026.116254_bib0185","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.asoc.2026.116254_bib0190","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","article-title":"Revisiting heterophily for graph neural networks","author":"Luan","year":"2022"},{"key":"10.1016\/j.asoc.2026.116254_bib0195","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"5449","article-title":"Representation learning on graphs with jumping knowledge networks","author":"Xu","year":"2018"},{"key":"10.1016\/j.asoc.2026.116254_bib0200","article-title":"Neighborhood convolutional graph neural network","author":"Chen","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.asoc.2026.116254_bib0205","series-title":"Proceedings of the International Conference on Machine Learning","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.1016\/j.asoc.2026.116254_bib0210","series-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","article-title":"NodeFormer: a scalable graph structure learning transformer for node classification","author":"Wu","year":"2022"},{"key":"10.1016\/j.asoc.2026.116254_bib0215","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Dualformer: dual graph transformer","author":"Zhuo","year":"2025"},{"issue":"4","key":"10.1016\/j.asoc.2026.116254_bib0220","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.1109\/TBDATA.2024.3524081","article-title":"NAGphormer+: a tokenized graph transformer with neighborhood augmentation for node classification in large graphs","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.asoc.2026.116254_bib0225","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"VCR-graphormer: a mini-batch graph transformer via virtual connections","author":"Fu","year":"2024"},{"key":"10.1016\/j.asoc.2026.116254_bib0230","series-title":"Proceedings of International Conference on Machine Learning, ICML","first-page":"43423","article-title":"The benefits of mixup for feature learning","author":"Zou","year":"2023"},{"key":"10.1016\/j.asoc.2026.116254_bib0235","series-title":"Proceedings of the World Wide Web Conference","article-title":"Heterogeneous graph attention network","author":"Wang","year":"2019"},{"key":"10.1016\/j.asoc.2026.116254_bib0240","series-title":"Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence","first-page":"4022","article-title":"Block modeling-guided graph convolutional neural networks","author":"He","year":"2022"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626017023?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626017023?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T07:49:31Z","timestamp":1789199371000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626017023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":48,"alternative-id":["S1568494626017023"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.116254","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dual token mixing-based graph transformer for semi-supervised node classification in attributed networks","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.116254","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116254"}}