{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T10:55:43Z","timestamp":1786704943432,"version":"3.56.0"},"reference-count":198,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576075"],"award-info":[{"award-number":["62576075"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tnnls.2025.3646122","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:47Z","timestamp":1768255307000},"page":"3052-3071","source":"Crossref","is-referenced-by-count":28,"title":["Graph Transformers: A Survey"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2116-2183","authenticated-orcid":false,"given":"Ahsan","family":"Shehzad","sequence":"first","affiliation":[{"name":"School of Software, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8324-1859","authenticated-orcid":false,"given":"Feng","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computing Technologies, RMIT University, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5024-8880","authenticated-orcid":false,"given":"Shagufta","family":"Abid","sequence":"additional","affiliation":[{"name":"School of Software, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3580-5402","authenticated-orcid":false,"given":"Ciyuan","family":"Peng","sequence":"additional","affiliation":[{"name":"Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1124-9509","authenticated-orcid":false,"given":"Shuo","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7683-5560","authenticated-orcid":false,"given":"Dongyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Foreign Languages and the School of Software Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8661-1544","authenticated-orcid":false,"given":"Karin","family":"Verspoor","sequence":"additional","affiliation":[{"name":"School of Computing Technologies, RMIT University, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2023.102538"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17594-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3118815"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2024.100417"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3304385"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3191784"},{"key":"ref11","first-page":"28877","article-title":"Do transformers really perform badly for graph representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ying"},{"key":"ref12","article-title":"Attending to graph transformers","author":"M\u00fcller","year":"Mar. 2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1060"},{"key":"ref16","first-page":"1","article-title":"A generalization of transformer networks to graphs","volume-title":"Proc. AAAI Workshop Deep Learn. Graphs, Methods Appl.","author":"Dwivedi"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3076021"},{"key":"ref18","article-title":"A survey on graph neural networks and graph transformers in computer vision: A task-oriented perspective","author":"Chen","year":"2022","journal-title":"arXiv:2209.13232"},{"key":"ref19","article-title":"Transformer for graphs: An overview from architecture perspective","author":"Min","year":"2022","journal-title":"arXiv:2202.08455"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2020.13"},{"key":"ref21","article-title":"How powerful are graph neural networks?","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref22","first-page":"23341","article-title":"How powerful are spectral graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref23","article-title":"A survey on spectral graph neural networks","author":"Bo","year":"2023","journal-title":"arXiv:2302.05631"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.06.006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121168"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.113"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.512"},{"key":"ref29","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956620"},{"key":"ref31","first-page":"11960","article-title":"Graph transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yun"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3108974"},{"key":"ref33","first-page":"12081","article-title":"Novel positional encodings to enable tree-based transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Shiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1054"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.236"},{"key":"ref36","article-title":"GRPE: Relative positional encoding for graph transformer","volume-title":"Proc. Mach. Learn. Drug Discovery","author":"Park"},{"key":"ref37","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75762-5_41"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2946825"},{"key":"ref40","article-title":"Deformable graph transformer","author":"Park","year":"2022","journal-title":"arXiv:2206.14337"},{"key":"ref41","article-title":"GraphiT: Encoding graph structure in transformers","author":"Mialon","year":"2021","journal-title":"arXiv:2106.05667"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.99"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.210"},{"key":"ref44","first-page":"11144","article-title":"Transformers meet directed graphs","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Geisler"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2952908"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-022-10066-8"},{"key":"ref47","first-page":"3469","article-title":"Structure-aware transformer for graph representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1986"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00146"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00244"},{"key":"ref51","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480095"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539296"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01151"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.640"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17478"},{"key":"ref59","article-title":"Graph inductive biases in transformers without message passing","author":"Ma","year":"2023","journal-title":"arXiv:2305.17589"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2023.3280577"},{"key":"ref61","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kreuzer"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.589"},{"key":"ref63","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref64","first-page":"3734","article-title":"Self-attention graph pooling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07366-3"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00214"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86362-3_21"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539121"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"ref70","first-page":"3962","article-title":"From block-Toeplitz matrices to differential equations on graphs: Towards a general theory for scalable masked transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Choromanski"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0748"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1312"},{"key":"ref74","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00218"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00352"},{"key":"ref77","first-page":"6476","article-title":"SMYRF: Efficient attention using asymmetric clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Daras"},{"key":"ref78","article-title":"Reformer: The efficient transformer","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Kitaev"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-40245-7_10"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-023-00698-9"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref82","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hamilton"},{"key":"ref83","first-page":"1","article-title":"Learnable graph convolutional attention networks","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Javaloy"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2933609"},{"key":"ref85","article-title":"Specformer: Spectral graph neural networks meet transformers","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Bo"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524258"},{"key":"ref87","article-title":"Are more layers beneficial to graph transformers?","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref88","article-title":"How attentive are graph attention networks?","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Brody"},{"key":"ref89","article-title":"Uncovering more shallow heuristics: Probing the natural language inference capacities of transformer-based pre-trained language models using syllogistic patterns","author":"Gubelmann","year":"2022","journal-title":"arXiv:2201.07614"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3124061"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3105544"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2972751"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2678"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3336894"},{"key":"ref95","article-title":"DeeperGCN: All you need to train deeper GCNs","author":"Li","year":"2020","journal-title":"arXiv:2006.07739"},{"key":"ref96","first-page":"2284","article-title":"Text generation from knowledge graphs with graph transformers","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Koncel-Kedziorski"},{"key":"ref97","first-page":"11548","article-title":"Self-supervised graph-level representation learning with local and global structure","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref98","first-page":"1390","article-title":"Systematic generalization with edge transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bergen"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1315-z"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-022-04812-w"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-020-03677-1"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475439"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103721"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3283879"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3149888"},{"key":"ref106","article-title":"DIFFormer: Scalable (graph) transformers induced by energy constrained diffusion","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977653.ch50"},{"key":"ref108","article-title":"DiGress: Discrete denoising diffusion for graph generation","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Vignac"},{"key":"ref109","first-page":"31613","article-title":"Exphormer: Sparse transformers for graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shirzad"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/523"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517872"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3206888"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.ces.2023.119057"},{"key":"ref114","article-title":"Transforming graphs for enhanced attribute clustering: An innovative graph transformer-based method","author":"Han","year":"2023","journal-title":"arXiv:2306.11307"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1539"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3269219"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.555"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.207"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/825"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26536"},{"key":"ref122","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rong"},{"key":"ref123","article-title":"ChemBERTa: Large-scale self-supervised pretraining for molecular property prediction","author":"Chithrananda","year":"2020","journal-title":"arXiv:2010.09885"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00384"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.501"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583441"},{"key":"ref127","article-title":"Towards effective and generalizable fine-tuning for pre-trained molecular graph models","author":"Xia","year":"Feb. 2022","journal-title":"bioRxiv"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539426"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583301"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591716"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29112"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539472"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102895"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref136","first-page":"2177","article-title":"Virtual node tuning for few-shot node classification","volume-title":"Proc. 29th ACM SIGKDD Conf. Knowl. Discovery Data Mining","author":"Tan"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10321-2"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1038\/s41580-022-00488-5"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad410"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30923-6_7"},{"key":"ref141","article-title":"DProQ: A gated-graph transformer for protein complex structure assessment","author":"Chen","year":"2022","journal-title":"arXiv:2205.10627"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2898191"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00129-1_4"},{"key":"ref144","article-title":"A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection","author":"Jin","year":"2023","journal-title":"arXiv:2307.03759"},{"key":"ref145","article-title":"Anomaly transformer: Time series anomaly detection with association discrepancy","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3100509"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514067"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201830"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3234761"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615127"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinthera.2023.01.002"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05593-6"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac162"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-19999-4"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3262937"},{"key":"ref156","article-title":"Pre-training transformers for knowledge graph completion","author":"Chen","year":"2023","journal-title":"arXiv:2303.15682"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.3390\/math11051073"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3282907"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539473"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591723"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3440269"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1016\/j.ddtec.2020.05.001"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23720-w"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45566-8"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3294998"},{"key":"ref167","first-page":"1","article-title":"PatchGT: Transformer over non-trainable clusters for learning graph representations","volume-title":"Proc. Learn. Graphs Conf.","author":"Gao"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583464"},{"key":"ref169","article-title":"AGFormer: Efficient graph representation with anchor-graph transformer","author":"Jiang","year":"2023","journal-title":"arXiv:2305.07521"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113679"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3264519"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/ISML60050.2024.11007399"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40292-0_19"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08687-7"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185320"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.694"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref179","article-title":"Text-to-image cross-modal generation: A systematic review","author":"\u017belaszczyk","year":"2024","journal-title":"arXiv:2401.11631"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"ref182","first-page":"11307","article-title":"Generative video transformer: Can objects be the words?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref183","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021","journal-title":"arXiv:2104.10157"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1145\/3653298"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807452"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3177455"},{"key":"ref188","first-page":"1","article-title":"DropEdge: Towards deep graph convolutional networks on node classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rong"},{"key":"ref189","first-page":"8058","article-title":"A comprehensive survey on graph reduction: Sparsification, coarsening, and condensation","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Hashemi"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1137\/s1064827595287997"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1145\/3571808"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref193","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3221100"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2022.3222049"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3416328"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183903"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11600559\/11345288.pdf?arnumber=11345288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T19:44:17Z","timestamp":1783626257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":198,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3646122","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}