{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:10:49Z","timestamp":1777871449990,"version":"3.51.4"},"reference-count":48,"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\/501100018571","name":"Specific Research Project of Guangxi for Research Bases and Talents","doi-asserted-by":"publisher","award":["GuiKe AD24010011"],"award-info":[{"award-number":["GuiKe AD24010011"]}],"id":[{"id":"10.13039\/501100018571","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017691","name":"Guangxi Key Research and Development Program","doi-asserted-by":"publisher","award":["GuiKe AB25069095"],"award-info":[{"award-number":["GuiKe AB25069095"]}],"id":[{"id":"10.13039\/501100017691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.115905","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:50:26Z","timestamp":1774939826000},"page":"115905","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["LiSA: A linear graph transformer framework with sample aggregation"],"prefix":"10.1016","volume":"342","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6840-7420","authenticated-orcid":false,"given":"Qian","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5506-8913","authenticated-orcid":false,"given":"Qingfeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4381-7497","authenticated-orcid":false,"given":"Shiyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-527X","authenticated-orcid":false,"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.knosys.2026.115905_bib0001","doi-asserted-by":"crossref","first-page":"6295","DOI":"10.1007\/s10462-022-10321-2","article-title":"A survey of graph neural networks in various learning paradigms: methods, applications, and challenges","volume":"56","author":"Waikhom","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.knosys.2026.115905_bib0002","series-title":"Technical Report","article-title":"Graph neural networks for graphs with heterophily: A survey","author":"Zheng","year":"2022"},{"key":"10.1016\/j.knosys.2026.115905_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110036","article-title":"A survey on deep learning based knowledge tracing","volume":"258","author":"Song","year":"2022","journal-title":"Knowl. Based Syst."},{"issue":"6","key":"10.1016\/j.knosys.2026.115905_bib0004","first-page":"5879","article-title":"Graph self-supervised learning: a survey","volume":"35","author":"Liu","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"10.1016\/j.knosys.2026.115905_bib0005","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/s13278-024-01371-1","article-title":"Enhancing social and collaborative learning using a stacked gnn-based community detection","volume":"14","author":"N","year":"2024","journal-title":"Soc. Netw. Anal. Min."},{"key":"10.1016\/j.knosys.2026.115905_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113217","article-title":"Semantic relation-aware graph attention network with noise augmented layer-wise contrastive learning for recommendation","volume":"314","author":"Liu","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103213","article-title":"Alzheimer\u2019s disease diagnosis from multi-modal data via feature inductive learning and dual multilevel graph neural network","volume":"97","author":"Lei","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.knosys.2026.115905_bib0008","doi-asserted-by":"crossref","first-page":"3335","DOI":"10.1016\/j.csbj.2020.10.022","article-title":"Inductive inference of gene regulatory network using supervised and semi-supervised graph neural networks","volume":"18","author":"Wang","year":"2020","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"10.1016\/j.knosys.2026.115905_bib0009","series-title":"Cross-skeleton interaction graph aggregation network for representation learning of mouse social behaviour","first-page":"623","volume":"34","author":"Zhou","year":"2025"},{"issue":"1","key":"10.1016\/j.knosys.2026.115905_bib0010","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1093\/bioinformatics\/btac759","article-title":"Deeprank-gnn: a graph neural network framework to learn patterns in protein-protein interfaces","volume":"39","author":"R\u00e9au","year":"2023","journal-title":"Bioinformatics"},{"issue":"1","key":"10.1016\/j.knosys.2026.115905_bib0011","article-title":"A graph transformer with optimized attention scores for node classification","volume":"15","author":"Zhang","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.knosys.2026.115905_bib0012","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0013","series-title":"Technical Report","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"4","key":"10.1016\/j.knosys.2026.115905_bib0014","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.26599\/BDMA.2024.9020034","article-title":"Transformer-based single-cell language model: a survey","volume":"7","author":"Lan","year":"2024","journal-title":"Big Data Mining Anal."},{"key":"10.1016\/j.knosys.2026.115905_bib0015","article-title":"Graph transformer networks","volume":"32","author":"Yun","year":"2019","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0016","first-page":"14582","article-title":"Pure transformers are powerful graph learners","volume":"35","author":"Kim","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0017","series-title":"Learning global dependencies via parallelized graph transformer with hybrid attention","first-page":"14157","volume":"327","author":"Duan","year":"2025"},{"key":"10.1016\/j.knosys.2026.115905_bib0018","series-title":"Kdlgt: a linear graph transformer framework via kernel decomposition approach","first-page":"2370","author":"Wu","year":"2023"},{"key":"10.1016\/j.knosys.2026.115905_bib0019","first-page":"14501","article-title":"Recipe for a general, powerful, scalable graph transformer","volume":"35","author":"Ramp\u00e1\u0161ek","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0020","first-page":"27387","article-title":"Nodeformer: a scalable graph structure learning transformer for node classification","volume":"35","author":"Wu","year":"2022","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0021","first-page":"5156","article-title":"Transformers are rnns: fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020"},{"key":"10.1016\/j.knosys.2026.115905_bib0022","series-title":"Polynormer: Polynomial-expressive graph transformer in linear time","author":"Deng","year":"2024"},{"issue":"Suppl 2","key":"10.1016\/j.knosys.2026.115905_bib0023","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1007\/s10462-023-10577-2","article-title":"Attention-based graph neural networks: a survey","volume":"56","author":"Sun","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.knosys.2026.115905_bib0024","first-page":"35","article-title":"Hydra attention: Efficient attention with many heads","author":"Bolya","year":"2022"},{"key":"10.1016\/j.knosys.2026.115905_bib0025","first-page":"5961","article-title":"Flatten transformer: vision transformer using focused linear attention","author":"Han","year":"2023"},{"key":"10.1016\/j.knosys.2026.115905_bib0026","series-title":"Technical Report","article-title":"Transformer for graphs: An overview from architecture perspective","author":"Min","year":"2022"},{"key":"10.1016\/j.knosys.2026.115905_bib0027","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1016\/j.ins.2021.08.100","article-title":"Jkt: a joint graph convolutional network based deep knowledge tracing","volume":"580","author":"Song","year":"2021","journal-title":"Inf. Sci."},{"issue":"2","key":"10.1016\/j.knosys.2026.115905_bib0028","first-page":"1296","article-title":"Combining graph neural networks with expert knowledge for smart contract vulnerability detection","volume":"35","author":"Liu","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.115905_bib0029","series-title":"Uncertainty-aware graph neural networks: a multihop evidence fusion approach","first-page":"18463","volume":"36","author":"Chen","year":"2025"},{"key":"10.1016\/j.knosys.2026.115905_bib0030","series-title":"Technical Report","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.knosys.2026.115905_bib0031","series-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017"},{"key":"10.1016\/j.knosys.2026.115905_bib0032","series-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"10.1016\/j.knosys.2026.115905_bib0033","series-title":"Hierarchical graph representation learning with differentiable pooling","first-page":"31","author":"Ying","year":"2018"},{"key":"10.1016\/j.knosys.2026.115905_bib0034","first-page":"32","article-title":"Provably powerful graph networks","author":"Maron","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0035","series-title":"Mirage: Model-agnostic graph distillation for graph classification","author":"Gupta","year":"2023"},{"key":"10.1016\/j.knosys.2026.115905_bib0036","series-title":"2024 IEEE International Conference on Systems, Man, and Cybernetics","first-page":"1544","article-title":"Incorporating heterophily into graph neural networks for graph classification","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.115905_bib0037","first-page":"7793","article-title":"Beyond homophily in graph neural networks: current limitations and effective designs","volume":"33","author":"Zhu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0038","doi-asserted-by":"crossref","unstructured":"F. Shahid, W. Rahman, A.B. Islam, N. Paul, N. Khan, M.S. Rahman, M.M. Haque, A.A.A. Islam, Two tell-tale perspectives of ptsd: neurobiological abnormalities and bayesian regulatory network of the underlying disorder in a refugee context, proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 3 (3) (2019) 1\u201345.","DOI":"10.1145\/3351259"},{"issue":"4","key":"10.1016\/j.knosys.2026.115905_bib0039","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3056563","article-title":"Graph-based fraud detection in the face of camouflage","volume":"11","author":"Hooi","year":"2017","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.1016\/j.knosys.2026.115905_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110739","article-title":"Exploring attention mechanism for graph similarity learning","volume":"276","author":"Tan","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0041","series-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"10.1016\/j.knosys.2026.115905_bib0042","series-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"10.1016\/j.knosys.2026.115905_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.108665","article-title":"Deep linear graph attention model for attributed graph clustering","volume":"246","author":"Liao","year":"2022","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0044","series-title":"Tudataset: A collection of benchmark datasets for learning with graphs","author":"Morris","year":"2020"},{"key":"10.1016\/j.knosys.2026.115905_bib0045","series-title":"Technical Report","article-title":"How attentive are graph attention networks?","author":"Brody","year":"2021"},{"key":"10.1016\/j.knosys.2026.115905_bib0046","series-title":"Technical Report","article-title":"How to find your friendly neighborhood: Graph attention design with self-supervision","author":"Kim","year":"2022"},{"key":"10.1016\/j.knosys.2026.115905_bib0047","article-title":"Generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.knosys.2026.115905_bib0048","first-page":"1285","article-title":"Transgnn: harnessing the collaborative power of transformers and graph neural networks for recommender systems","author":"Zhang","year":"2024"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126006313?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126006313?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:16:49Z","timestamp":1777569409000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126006313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":48,"alternative-id":["S0950705126006313"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115905","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LiSA: A linear graph transformer framework with sample aggregation","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115905","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":"115905"}}