{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T22:10:22Z","timestamp":1784412622949,"version":"3.55.0"},"reference-count":300,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFC3307900"],"award-info":[{"award-number":["2024YFC3307900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62436003"],"award-info":[{"award-number":["62436003"]}],"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":["62376103"],"award-info":[{"award-number":["62376103"]}],"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":["62206102"],"award-info":[{"award-number":["62206102"]}],"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":["62302184"],"award-info":[{"award-number":["62302184"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005064","name":"Hebei Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["2022BAA046"],"award-info":[{"award-number":["2022BAA046"]}],"id":[{"id":"10.13039\/501100005064","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hubei science and technology talent service project","award":["2024DJC078"],"award-info":[{"award-number":["2024DJC078"]}]},{"DOI":"10.13039\/100018735","name":"Ant Group","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018735","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Ant Research Fund"},{"name":"HPC Platform of Huazhong University of Science and Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tkde.2025.3568147","type":"journal-article","created":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T13:40:43Z","timestamp":1746711643000},"page":"4389-4410","source":"Crossref","is-referenced-by-count":6,"title":["A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3565-4170","authenticated-orcid":false,"given":"Ziwen","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0553-9163","authenticated-orcid":false,"given":"Yixin","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1846-4941","authenticated-orcid":false,"given":"Yuhua","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2125-9041","authenticated-orcid":false,"given":"Yixiong","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7791-5511","authenticated-orcid":false,"given":"Ruixuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8132-6250","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3542609"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref4","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref5","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref6","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref7","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rong"},{"key":"ref8","first-page":"28798","article-title":"GraphFormers: GNN-nested transformers for representation learning on textual graph","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref9","article-title":"Node feature extraction by self-supervised multi-scale neighborhood prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chien"},{"key":"ref10","article-title":"Harnessing explanations: LLM-to-LM interpreter for enhanced text-attributed graph representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He"},{"key":"ref11","first-page":"1955","article-title":"Language is all a graph needs","volume-title":"Proc. Eur. Conf. Field Comput. Linguistics Findings","author":"Ye"},{"key":"ref12","article-title":"Variational graph auto-encoders","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Kipf"},{"key":"ref13","article-title":"Deep graph infomax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3548729"},{"key":"ref15","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref16","article-title":"A survey of pretraining on graphs: Taxonomy, methods, and applications","author":"Xia","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170559"},{"key":"ref18","article-title":"Graph meets LLMs: Towards large graph models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Zhang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3469578"},{"key":"ref20","article-title":"Graph machine learning in the era of large language models (LLMs)","author":"Fan","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671460"},{"key":"ref22","first-page":"34670","article-title":"Position: Graph foundation models are already here","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539321"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512211"},{"key":"ref25","article-title":"Towards graph contrastive learning: A survey and beyond","author":"Ju","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6048"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132967"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00662"},{"key":"ref30","article-title":"Graph-BERT: Only attention is needed for learning graph representations","author":"Zhang","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380112"},{"key":"ref32","article-title":"Strategies for pre-training graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref33","first-page":"10871","article-title":"When does self-supervision help graph convolutional networks?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref34","article-title":"Self-supervised learning on graphs: Deep insights and new direction","author":"Jin","year":"2020"},{"key":"ref35","first-page":"24460","article-title":"Self-supervised representation learning via latent graph prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref36","first-page":"22667","article-title":"SLAPS: Self-supervision improves structure learning for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fatemi"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583379"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26192"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv-2023-dngg4","article-title":"Mole-BERT: Rethinking pre-training graph neural networks for molecules","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xia"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00223"},{"key":"ref42","article-title":"Deep graph contrastive representation learning","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop (GRL+)","author":"Zhu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449802"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/204"},{"key":"ref45","first-page":"24332","article-title":"ProGCL: Rethinking hard negative mining in graph contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xia"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539425"},{"key":"ref47","first-page":"20407","article-title":"Contrastive graph structure learning via information bottleneck for recommendation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref48","article-title":"Large-scale representation learning on graphs via bootstrapping","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Thakoor"},{"key":"ref49","first-page":"115351","article-title":"Exploitation of a latent mechanism in graph contrastive learning: Representation scattering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"He"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20748"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531937"},{"key":"ref52","article-title":"LightGCL: Simple yet effective graph contrastive learning for recommendation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26319"},{"key":"ref54","first-page":"32465","article-title":"Uncovering the structural fairness in graph contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref55","article-title":"Single-pass contrastive learning can work for both homophilic and heterophilic graph","author":"Wang","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645614"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109631"},{"key":"ref58","first-page":"76","article-title":"From canonical correlation analysis to self-supervised graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref59","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bardes"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671914"},{"key":"ref61","article-title":"Unsupervised pre-training of graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations Workshop Representation Learn. Graphs Manifolds","author":"Hu"},{"key":"ref62","article-title":"Graph auto-encoder via neighborhood Wasserstein reconstruction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tang"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599546"},{"key":"ref64","first-page":"9559","article-title":"Permutation-invariant variational autoencoder for graph-level representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Winter"},{"key":"ref65","article-title":"Centrality-guided pre-training for graph","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/362"},{"key":"ref67","first-page":"10712","article-title":"Semi-implicit graph variational auto-encoders","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hasanzadeh"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539249"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570404"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645370"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17206"},{"key":"ref72","article-title":"How to find your friendly neighborhood: Graph attention design with self-supervision","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635769"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645601"},{"key":"ref75","first-page":"1766","article-title":"Transfer learning of graph neural networks with ego-graph information maximization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25618"},{"key":"ref77","first-page":"5682","article-title":"Contrastive Laplacian Eigenmaps","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref78","first-page":"30783","article-title":"Generalized Laplacian Eigenmaps","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70344-7_12"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25898"},{"key":"ref82","article-title":"Graph-MLP: Node classification without message passing in graph","author":"Hu","year":"2021"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01612"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00031"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20700"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557478"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714611"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.046"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403140"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403177"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25536"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25858"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3264512"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3288280"},{"key":"ref95","first-page":"15870","article-title":"Motif-based graph self-supervised learning for molecular property prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref96","first-page":"17584","article-title":"Fragment-based pretraining and finetuning on molecular graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Luong"},{"key":"ref97","article-title":"Motif-aware attribute masking for molecular graph pre-training","volume-title":"Proc. 3rd Learn. Graphs Conf.","author":"Inae"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28774"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28754"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3364059"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645470"},{"key":"ref102","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":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599380"},{"key":"ref104","first-page":"52801","article-title":"From coarse to fine: Enable comprehensive graph self-supervised learning with multi-granular semantic ensemble","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wen"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599268"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29016"},{"key":"ref107","first-page":"5274","article-title":"Dirichlet graph variational autoencoder","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449899"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512208"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/229"},{"key":"ref111","article-title":"StructComp: Substituting propagation with structural compression in training graph contrastive learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref112","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"You"},{"key":"ref113","first-page":"12121","article-title":"Graph contrastive learning automated","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref114","first-page":"15920","article-title":"Adversarial graph augmentation to improve graph contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Suresh"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512156"},{"key":"ref116","article-title":"InfoGraph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sun"},{"key":"ref117","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hassani"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20349"},{"key":"ref119","first-page":"10809","article-title":"Rethinking and scaling up graph contrastive learning: An extremely efficient approach with group discrimination","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref120","first-page":"14085","article-title":"Graph self-supervised learning with accurate discrepancy learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583499"},{"key":"ref122","article-title":"Spectral augmentation for self-supervised learning on graphs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref123","article-title":"Pre-training graph neural networks with kernels","author":"Navarin","year":"2018"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29255"},{"key":"ref125","first-page":"4575","article-title":"Enhancing hyperbolic graph embeddings via contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Liu"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20333"},{"key":"ref127","article-title":"Graph-level representation learning with joint-embedding predictive architectures","author":"Skenderi","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref128","first-page":"637","article-title":"Graph representation learning in hyperbolic space via dual-masked","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Gong"},{"key":"ref129","first-page":"1154","article-title":"RiemannGFM: Learning a graph foundation model from structural geometry","volume-title":"Proc. Int. Conf. World Wide Web","author":"Sun"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709277"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref135","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belghazi"},{"key":"ref136","first-page":"271","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nowozin"},{"key":"ref137","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref140","first-page":"452","article-title":"BPR: Bayesian personalized ranking from implicit feedback","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Rendle"},{"key":"ref141","first-page":"5000","article-title":"Provable guarantees for self-supervised deep learning with spectral contrastive loss","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"HaoChen"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583386"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645620"},{"key":"ref144","first-page":"12310","article-title":"Barlow Twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1038\/30918"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.387"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29596"},{"key":"ref149","article-title":"Is homophily a necessity for graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0080"},{"key":"ref152","first-page":"16302","article-title":"PRODIGY: Enabling in-context learning over graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599256"},{"key":"ref154","article-title":"One for All: Towards training one graph model for all classification tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289026"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-8137.1912.tb05611.x"},{"key":"ref157","article-title":"ULTRA-DP: Unifying graph pre-training with multi-task graph dual prompt","author":"Chen","year":"2023"},{"key":"ref158","volume-title":"In Silico Medicinal Chemistry: Computational Methods to Support Drug Design","author":"Brown","year":"2015"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-017-0225-z"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_30"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16552"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00219"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599548"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28755"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645439"},{"key":"ref168","first-page":"107403","article-title":"GFT: Graph foundation model with transferable tree vocabulary","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467450"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/518"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29156"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29264"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29112"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645703"},{"key":"ref175","article-title":"HG-Adapter: Improving pre-trained heterogeneous graph neural networks with dual adapters","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mo"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714917"},{"key":"ref177","first-page":"52464","article-title":"Universal prompt tuning for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fang"},{"key":"ref178","article-title":"Instance-aware graph prompt learning","author":"Li","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref179","article-title":"Deep prompt tuning for graph transformers","author":"Shirkavand","year":"2023"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70362-1_25"},{"key":"ref181","first-page":"2177","article-title":"Virtual node tuning for few-shot node classification","volume-title":"Proc. Int. Conf. Knowl. Discov. Data Mining","author":"Tan"},{"key":"ref182","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4637382","article-title":"SGL-PT: A strong graph learner with graph prompt tuning","author":"Zhu","year":"2023"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645685"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671742"},{"key":"ref185","article-title":"Edge prompt tuning for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714780"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3419109"},{"key":"ref188","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4868575","article-title":"Subgraph-level universal prompt tuning","author":"Lee","year":"2024"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709219"},{"key":"ref190","article-title":"GCoT: Chain-of-thought prompt learning for graphs","author":"Yu","year":"2025"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645423"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671952"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645546"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671804"},{"key":"ref195","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref196","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref197","article-title":"Graph prompt learning: A comprehensive survey and beyond","author":"Sun","year":"2023"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.692"},{"key":"ref199","article-title":"Path-LLM: A shortest-path-based LLM learning for unified graph representation","author":"Shang","year":"2024"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599833"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591641"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.181"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.textgraphs-1.2"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657775"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1145\/3701551.3703586"},{"key":"ref206","article-title":"A pure transformer pretraining framework on text-attributed graphs","volume-title":"Proc. Learn. Graphs Conf.","author":"Song"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.97"},{"key":"ref208","first-page":"30840","article-title":"Can language models solve graph problems in natural language?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref209","article-title":"Beyond text: A deep dive into large language models\u2019 ability on understanding graph data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop New Front. Graph Learn.","author":"Hu"},{"key":"ref210","article-title":"Talk like a graph: Encoding graphs for large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fatemi"},{"key":"ref211","article-title":"Can LLMs effectively leverage graph structural information through prompts, and why?","author":"Huang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref212","first-page":"141045","article-title":"Can large language models analyze graphs like professionals? A benchmark, datasets and models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref213","article-title":"Similarity-based neighbor selection for graph LLMs","author":"Li","year":"2024"},{"key":"ref214","article-title":"Graph reasoning with large language models via pseudo-code prompting","author":"Skianis","year":"2024"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.75"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671709"},{"key":"ref217","article-title":"Let your graph do the talking: Encoding structured data for LLMs","author":"Perozzi","year":"2024"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651476"},{"key":"ref219","article-title":"Prompt-based node feature extractor for few-shot learning on text-attributed graphs","author":"Huang","year":"2023"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645627"},{"key":"ref221","article-title":"Disentangled representation learning with large language models for text-attributed graphs","author":"Qin","year":"2023"},{"key":"ref222","article-title":"GOFA: A generative one-for-all model for joint graph language modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong"},{"key":"ref223","article-title":"TAGA: Text-attributed graph self-supervised learning by synergizing graph and text mutual transformations","author":"Zhang","year":"2024"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714801"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679830"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/634"},{"key":"ref227","first-page":"5950","article-title":"LLMs as zero-shot graph learners: Alignment of GNN representations with LLM token embeddings","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671987"},{"key":"ref229","first-page":"7809","article-title":"LLaGA: Large language and graph assistant","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref230","article-title":"Improving molecule-language alignment with hierarchical graph tokenization","author":"Chen","year":"2024"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645682"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1145\/3655103.3655110"},{"key":"ref233","article-title":"Can large language models empower molecular property prediction?","author":"Qian","year":"2023"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.65"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672035"},{"key":"ref236","article-title":"Scale-free graph-language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu"},{"key":"ref237","article-title":"Label-free node classification on graphs with large language models (LLMs)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709256"},{"key":"ref239","article-title":"Leveraging large language models for effective label-free node classification in text-attributed graphs","volume-title":"Proc. Int. ACM SIGIR Conf. Res. Develop. Informat. Retrieval","author":"Zhang","year":"2025"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33428"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.132"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1145\/3701551.3703488"},{"key":"ref243","article-title":"Large language models as topological structure enhancers for text-attributed graphs","volume-title":"Proc. Int. Conf. Database Syst. Adv. Appl.","author":"Sun","year":"2025"},{"key":"ref244","article-title":"Learning on large-scale text-attributed graphs via variational inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao"},{"key":"ref245","article-title":"GraphLLM: Boosting graph reasoning ability of large language model","author":"Chai","year":"2023"},{"key":"ref246","article-title":"Efficient large language models fine-tuning on graphs","author":"Xue","year":"2023"},{"key":"ref247","article-title":"SimTeG: A frustratingly simple approach improves textual graph learning","author":"Duan","year":"2023"},{"key":"ref248","first-page":"13308","article-title":"WalkLM: A uniform language model fine-tuning framework for attributed graph embedding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tan"},{"key":"ref249","article-title":"GUNDAM: Aligning large language models with graph understanding","author":"Ouyang","year":"2024"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33901"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.801"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672010"},{"key":"ref253","article-title":"GraphInstruct: Empowering large language models with graph understanding and reasoning capability","author":"Luo","year":"2024"},{"key":"ref254","article-title":"How to make LLMs strong node classifiers?","author":"Xu","year":"2024"},{"key":"ref255","article-title":"HierPromptLM: A pure PLM-based framework for representation learning on heterogeneous text-rich networks","author":"Zhu","year":"2025"},{"key":"ref256","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref257","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI"},{"key":"ref258","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref259","article-title":"Deepseek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning","year":"2025"},{"key":"ref260","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref262","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/898"},{"key":"ref264","article-title":"GraphText: Graph reasoning in text space","author":"Zhao","year":"2023"},{"key":"ref265","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref267","article-title":"Automated self-supervised learning for graphs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jin"},{"key":"ref268","article-title":"Multi-task self-supervised graph neural networks enable stronger task generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ju"},{"key":"ref269","first-page":"12957","article-title":"Exploring correlations of self-supervised tasks for graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fang"},{"key":"ref270","article-title":"Automated graph self-supervised learning via multi-teacher knowledge distillation","author":"Wu","year":"2022"},{"key":"ref271","article-title":"Decoupling weighing and selecting for integrating multiple graph pre-training tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599376"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671719"},{"key":"ref274","first-page":"10294","article-title":"Self-supervised auxiliary learning with meta-paths for heterogeneous graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hwang"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467415"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467396"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.4324\/9780203786031-11"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00360"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511945"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3325484"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29875"},{"key":"ref282","first-page":"70229","article-title":"GPT-ST: Generative pre-training of spatio-temporal graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679554"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482389"},{"key":"ref285","article-title":"Node-time conditional prompt learning in dynamic graphs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645454"},{"key":"ref287","first-page":"1909","article-title":"Augmentations in hypergraph contrastive learning: Fabricated and generative","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26019"},{"key":"ref289","article-title":"HypeBoy: Generative self-supervised representation learning on hypergraphs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref290","first-page":"17008","article-title":"Certifiably robust graph contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref291","first-page":"15862","article-title":"Co-modality graph contrastive learning for imbalanced node classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qian"},{"key":"ref292","article-title":"Learning fair graph representations via automated data augmentations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ling"},{"key":"ref293","first-page":"40888","article-title":"Graph contrastive backdoor attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671956"},{"key":"ref295","article-title":"Learning on graphs with large language models (LLMs): A deep dive into model robustness","author":"Guo","year":"2024"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.11"},{"key":"ref297","article-title":"Reasoning on graphs: Faithful and interpretable large language model reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luo"},{"key":"ref298","article-title":"Graph retrieval-augmented generation: A survey","author":"Peng","year":"2024"},{"key":"ref299","first-page":"132876","article-title":"G-Retriever: Retrieval-augmented generation for textual graph understanding and question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"He"},{"key":"ref300","first-page":"29948","article-title":"RAGraph: A general retrieval-augmented graph learning framework","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jiang"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11072530\/10992675.pdf?arnumber=10992675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T21:54:59Z","timestamp":1756245299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10992675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":300,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3568147","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}