{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T01:10:55Z","timestamp":1777338655766,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["72293575"],"award-info":[{"award-number":["72293575"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Science & Technology Commission","award":["Z231100007423016"],"award-info":[{"award-number":["Z231100007423016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tkde.2025.3591732","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T18:07:28Z","timestamp":1753207648000},"page":"6061-6074","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Level Task-Agnostic Graph Representation Learning With Isomorphic-Consistent Variational Graph Auto-Encoders"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4473-2356","authenticated-orcid":false,"given":"Hanxuan","family":"Yang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1929-8404","authenticated-orcid":false,"given":"Qingchao","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2323-5091","authenticated-orcid":false,"given":"Wenji","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512182"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539415"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"ref4","first-page":"2323","article-title":"Junction tree variational autoencoder for molecular graph generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3147790"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017370"},{"key":"ref7","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref8","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref9","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref10","article-title":"GraphSAINT: Graph sampling based inductive learning method","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng"},{"key":"ref11","article-title":"GraphENS: Neighbor-aware ego network synthesis for class-imbalanced node classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Park"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539121"},{"key":"ref13","article-title":"SCR: Training graph neural networks with consistency regularization","author":"Zhang","year":"2022"},{"key":"ref14","first-page":"5171","article-title":"Link prediction based on graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref15","first-page":"9061","article-title":"Labeling trick: A theory of using graph neural networks for multi-node representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref16","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref17","first-page":"8230","article-title":"G-Mixup: Graph data augmentation for graph classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25941"},{"key":"ref19","article-title":"Variational graph auto-encoders","volume-title":"Proc. NIPS Workshop Bayesian Deep Learn.","author":"Kipf"},{"key":"ref20","first-page":"10711","article-title":"Semi-implicit graph variational auto-encoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hasanzadeh"},{"key":"ref21","first-page":"5274","article-title":"Dirichlet graph variational autoencoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref22","first-page":"9559","article-title":"Permutation-invariant variational autoencoder for graph-level representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Winter"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3148272"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3380012"},{"key":"ref26","first-page":"2434","article-title":"Graphite: Iterative generative modeling of graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Grover"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00157"},{"key":"ref28","first-page":"21019","article-title":"Deconvolutional networks on graph data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref29","article-title":"Graph auto-encoder via neighborhood Wasserstein reconstruction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3133439"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28694"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icde65448.2025.00110"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539321"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599546"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11872"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16605"},{"key":"ref37","first-page":"13556","article-title":"Graph normalizing flows","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref38","first-page":"7192","article-title":"GraphDF: A discrete flow model for molecular graph generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Luo"},{"key":"ref39","first-page":"7939","article-title":"Improving graph generation by restricting graph bandwidth","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Diamant"},{"key":"ref40","article-title":"DiGress: Discrete denoising diffusion for graph generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Vignac"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3372123"},{"issue":"9","key":"ref42","first-page":"12","article-title":"A reduction of a graph to a canonical form and an algebra arising during this reduction","volume":"2","author":"Leman","year":"1968","journal-title":"Nauchno-Technicheskaya Informatsiya"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976700.38"},{"key":"ref44","first-page":"23341","article-title":"How powerful are spectral graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref45","article-title":"How powerful are K-hop message passing graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref46","first-page":"24737","article-title":"Path neural networks: Expressive and accurate graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Michel"},{"key":"ref47","first-page":"7090","article-title":"Universal invariant and equivariant graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Keriven"},{"key":"ref48","first-page":"10383","article-title":"Can graph neural networks count substructures?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref49","article-title":"What graph neural networks cannot learn: Depth vs width","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loukas"},{"key":"ref50","first-page":"3419","article-title":"Generalization and representational limits of graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Garg"},{"key":"ref51","article-title":"On graph neural networks versus graph-augmented MLPs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref52","article-title":"Rethinking the expressive power of GNNs via graph biconnectivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref53","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref54","article-title":"Deep graph infomax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref55","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":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3330684"},{"key":"ref57","first-page":"1338","article-title":"Conditional structure generation through graph variational generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/qss_a_00021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11163535\/11088232.pdf?arnumber=11088232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T05:42:31Z","timestamp":1757742151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11088232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":60,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3591732","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":[[2025,10]]}}}