{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:19:04Z","timestamp":1775503144297,"version":"3.50.1"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010852","name":"Institute of Computing Technology, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["E461060"],"award-info":[{"award-number":["E461060"]}],"id":[{"id":"10.13039\/501100010852","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDB0680201"],"award-info":[{"award-number":["XDB0680201"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576333"],"award-info":[{"award-number":["62576333"]}],"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":["62406307"],"award-info":[{"award-number":["62406307"]}],"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":["62476263"],"award-info":[{"award-number":["62476263"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["JQ25015"],"award-info":[{"award-number":["JQ25015"]}],"id":[{"id":"10.13039\/501100004826","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":[[2026,6]]},"DOI":"10.1016\/j.neunet.2026.108595","type":"journal-article","created":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T00:33:01Z","timestamp":1768609981000},"page":"108595","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Graph-Agnostic Linear Transformers"],"prefix":"10.1016","volume":"198","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4932-6429","authenticated-orcid":false,"given":"Zhiyu","family":"Guo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1525-0788","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9633-8361","authenticated-orcid":false,"given":"Xiang","family":"Ao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4190-227X","authenticated-orcid":false,"given":"Yateng","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4048-6604","authenticated-orcid":false,"given":"Xinhuan","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5597-1830","authenticated-orcid":false,"given":"Xuehao","family":"Zheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-5398","authenticated-orcid":false,"given":"Qing","family":"He","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108595_bib0001","unstructured":"Brody, S., Alon, U., & Yahav, E. (2021). How attentive are graph attention networks?arXiv preprint arXiv: 2105.14491."},{"key":"10.1016\/j.neunet.2026.108595_bib0002","series-title":"International conference on machine learning","first-page":"3469","article-title":"Structure-aware transformer for graph representation learning","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.108595_bib0003","series-title":"The eleventh international conference on learning representations","article-title":"Nagphormer: A tokenized graph transformer for node classification in large graphs","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.108595_bib0004","series-title":"International conference on machine learning","first-page":"1725","article-title":"Simple and deep graph convolutional networks","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.108595_bib0005","first-page":"19314","article-title":"Iterative deep graph learning for graph neural networks: Better and robust node embeddings","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0006","series-title":"Proceedings of the ACM on web conference 2025","first-page":"1237","article-title":"Spear: A structure-preserving manipulation method for graph backdoor attacks","author":"Ding","year":"2025"},{"key":"10.1016\/j.neunet.2026.108595_bib0007","unstructured":"Frasca, F., Rossi, E., Eynard, D., Chamberlain, B., Bronstein, M., & Monti, F. (2020). Sign: Scalable inception graph neural networks. arXiv preprint arXiv: 2004.11198."},{"key":"10.1016\/j.neunet.2026.108595_bib0008","unstructured":"Gasteiger, J., Bojchevski, A., & G\u00fcnnemann, S. (2018). Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv: 1810.05997."},{"key":"10.1016\/j.neunet.2026.108595_bib0009","doi-asserted-by":"crossref","first-page":"2059","DOI":"10.52202\/068431-0150","article-title":"Good: A graph out-of-distribution benchmark","volume":"35","author":"Gui","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0010","series-title":"Proceedings of the 31st ACM SIGKDD conference on knowledge discovery and data mining v. 2","first-page":"767","article-title":"Grasp: Differentially private graph reconstruction defense with structured perturbation","author":"Guo","year":"2025"},{"key":"10.1016\/j.neunet.2026.108595_bib0011","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0012","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"5961","article-title":"Flatten transformer: Vision transformer using focused linear attention","author":"Han","year":"2023"},{"key":"10.1016\/j.neunet.2026.108595_bib0013","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0014","series-title":"International conference on machine learning","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020"},{"key":"10.1016\/j.neunet.2026.108595_bib0015","unstructured":"Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv: 1609.02907."},{"key":"10.1016\/j.neunet.2026.108595_bib0016","series-title":"The twelfth international conference on learning representations","article-title":"Boosting the adversarial robustness of graph neural networks: An ood perspective","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.108595_bib0017","series-title":"The eleventh international conference on learning representations","article-title":"Revisiting graph adversarial attack and defense from a data distribution perspective","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.108595_bib0018","series-title":"International conference on machine learning","first-page":"13242","article-title":"Finding global homophily in graph neural networks when meeting heterophily","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.108595_bib0019","series-title":"Proceedings of the 32nd international joint conference on artificial intelligence (IJCAI-23)","first-page":"2196","article-title":"Gapformer: Graph transformer with graph pooling for node classification","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108595_bib0020","series-title":"Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"1131","article-title":"Ud-gnn: Uncertainty-aware debiased training on semi-homophilous graphs","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108595_bib0021","series-title":"Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"1548","article-title":"Flood: A flexible invariant learning framework for out-of-distribution generalization on graphs","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108595_bib0022","series-title":"Proceedings of the web conference 2021","first-page":"3168","article-title":"Pick and choose: A GNN-based imbalanced learning approach for fraud detection","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108595_bib0023","series-title":"Proceedings of the ACM web conference 2022","first-page":"1392","article-title":"Towards unsupervised deep graph structure learning","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108595_bib0024","unstructured":"Ma, L., Lin, C., Lim, D., Romero-Soriano, A., Dokania, P. K., Coates, M., Torr, P., & Lim, S.-N. (2023). Graph inductive biases in transformers without message passing. arXiv preprint arXiv: 2305.17589."},{"key":"10.1016\/j.neunet.2026.108595_bib0025","series-title":"Proceedings of the 30th ACM international conference on information & knowledge management","first-page":"1202","article-title":"A unified view on graph neural networks as graph signal denoising","author":"Ma","year":"2021"},{"key":"10.1016\/j.neunet.2026.108595_bib0026","doi-asserted-by":"crossref","unstructured":"Pal, S. K., & Mitra, S. (1992). Multilayer perceptron, fuzzy sets, classifiaction.","DOI":"10.1109\/72.159058"},{"key":"10.1016\/j.neunet.2026.108595_bib0027","unstructured":"Pei, H., Wei, B., Chang, K. C.-C., Lei, Y., & Yang, B. (2020). Geom-gcn: Geometric graph convolutional networks. arXiv preprint arXiv: 2002.05287."},{"key":"10.1016\/j.neunet.2026.108595_bib0028","unstructured":"Platonov, O., Kuznedelev, D., Diskin, M., Babenko, A., & Prokhorenkova, L. (2023). A critical look at the evaluation of GNNs under heterophily: Are we really making progress?arXiv preprint arXiv: 2302.11640."},{"key":"10.1016\/j.neunet.2026.108595_bib0029","doi-asserted-by":"crossref","unstructured":"Qin, Z., Han, X., Sun, W., Li, D., Kong, L., Barnes, N., & Zhong, Y. (2022). The devil in linear transformer. arXiv preprint arXiv: 2210.10340.","DOI":"10.18653\/v1\/2022.emnlp-main.473"},{"key":"10.1016\/j.neunet.2026.108595_bib0030","first-page":"14501","article-title":"Recipe for a general, powerful, scalable graph transformer","volume":"35","author":"Ramp\u00e1\u0161ek","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0031","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"3531","article-title":"Efficient attention: Attention with linear complexities","author":"Shen","year":"2021"},{"key":"10.1016\/j.neunet.2026.108595_bib0032","unstructured":"Shirzad, H., Velingker, A., Venkatachalam, B., Sutherland, D. J., & Sinop, A. K. (2023). Exphormer: Sparse transformers for graphs. arXiv preprint arXiv: 2303.06147."},{"issue":"3","key":"10.1016\/j.neunet.2026.108595_bib0033","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/MSP.2012.2235192","article-title":"The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains","volume":"30","author":"Shuman","year":"2013","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.neunet.2026.108595_bib0034","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0035","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. arXiv preprint arXiv: 1710.10903."},{"key":"10.1016\/j.neunet.2026.108595_bib0036","series-title":"International conference on machine learning","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2026.108595_bib0037","unstructured":"Wu, H., Wu, J., Xu, J., Wang, J., & Long, M. (2022a). Flowformer: Linearizing transformers with conservation flows. arXiv preprint arXiv: 2202.06258."},{"key":"10.1016\/j.neunet.2026.108595_bib0038","unstructured":"Wu, Q., Yang, C., Zhao, W., He, Y., Wipf, D., & Yan, J. (2023a). Difformer: Scalable (graph) transformers induced by energy constrained diffusion. arXiv preprint arXiv: 2301.09474."},{"key":"10.1016\/j.neunet.2026.108595_bib0039","first-page":"27387","article-title":"Nodeformer: A scalable graph structure learning transformer for node classification","volume":"35","author":"Wu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0040","unstructured":"Wu, Q., Zhao, W., Yang, C., Zhang, H., Nie, F., Jiang, H., Bian, Y., & Yan, J. (2023b). Simplifying and empowering transformers for large-graph representations. arXiv preprint arXiv: 2306.10759."},{"key":"10.1016\/j.neunet.2026.108595_bib0041","first-page":"13266","article-title":"Representing long-range context for graph neural networks with global attention","volume":"34","author":"Wu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0042","series-title":"International conference on machine learning","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","author":"Xu","year":"2018"},{"key":"10.1016\/j.neunet.2026.108595_bib0043","unstructured":"Ying, C., Cai, T., Luo, S., Zheng, S., Ke, G., He, D., Shen, Y., & Liu, T.-Y. (2021). Do transformers really perform bad for graph representation?(2021). https:\/\/arxiv.org\/abs\/2106.05234."},{"key":"10.1016\/j.neunet.2026.108595_bib0044","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13133","article-title":"Dynamic graph learning with static relations for credit risk assessment","volume":"vol. 39","author":"Yuan","year":"2025"},{"key":"10.1016\/j.neunet.2026.108595_bib0045","first-page":"21171","article-title":"Hierarchical graph transformer with adaptive node sampling","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108595_bib0046","unstructured":"Zhao, H., Ma, S., Zhang, D., Deng, Z.-H., & Wei, F. (2023a). Are more layers beneficial to graph transformers?arXiv preprint arXiv: 2303.00579."},{"key":"10.1016\/j.neunet.2026.108595_bib0047","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wu, Q., Yang, C., & Yan, J. (2023b). GraphGLOW: Universal and generalizable structure learning for graph neural networks. arXiv preprint arXiv: 2306.11264.","DOI":"10.1145\/3580305.3599373"},{"key":"10.1016\/j.neunet.2026.108595_bib0048","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.2026.108595_bib0049","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"},{"key":"10.1016\/j.neunet.2026.108595_bib0050","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"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026000572?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026000572?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T18:32:22Z","timestamp":1775500342000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026000572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":50,"alternative-id":["S0893608026000572"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108595","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Graph-Agnostic Linear Transformers","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108595","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":"108595"}}