{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:11:13Z","timestamp":1764839473199,"version":"3.46.0"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["2022YFB3102200"],"award-info":[{"award-number":["2022YFB3102200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402491","62376064","U23A20305","62472416"],"award-info":[{"award-number":["62402491","62376064","U23A20305","62472416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771524"],"award-info":[{"award-number":["2025M771524"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3610096","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:33:51Z","timestamp":1758044031000},"page":"1029-1044","source":"Crossref","is-referenced-by-count":0,"title":["Generative Causality-Driven Network for Graph Multi-Task Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6645-0597","authenticated-orcid":false,"given":"Xixun","family":"Lin","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4041-8390","authenticated-orcid":false,"given":"Qing","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0811-4016","authenticated-orcid":false,"given":"Yanan","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Lixin","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9958-8673","authenticated-orcid":false,"given":"Chuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1371-5801","authenticated-orcid":false,"given":"Jia","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computing, Macquarie University, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3144-6374","authenticated-orcid":false,"given":"Chenliang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7973-2746","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-527X","authenticated-orcid":false,"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Gold Coast, QLD, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3032227"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/ijms23052797"},{"key":"ref6","first-page":"1","article-title":"Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Sun","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2477843"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007637"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref10","first-page":"1755","article-title":"Sparse Bayesian multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Guo","year":"2011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10820"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.126"},{"key":"ref15","first-page":"1593","article-title":"Learning multiple tasks with multilinear relationship networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Long","year":"2017"},{"key":"ref16","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2020"},{"key":"ref17","first-page":"27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fifty","year":"2021"},{"key":"ref18","first-page":"2690","article-title":"Hierarchical multitask structured output learning for large-scale sequence segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"G\u00f6rnitz","year":"2011"},{"key":"ref19","first-page":"1039","article-title":"Learning to propagate for graph meta-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2019"},{"key":"ref20","first-page":"8906","article-title":"Structured multi-task learning for molecular property prediction","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Liu","year":"2022"},{"key":"ref21","first-page":"983","article-title":"Structured prediction energy networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belanger","year":"2016"},{"key":"ref22","first-page":"1723","article-title":"Learning task grouping and overlap in multi-task learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kumar","year":"2012"},{"key":"ref23","first-page":"615","article-title":"Learning multiple tasks with Kernel methods","volume":"6","author":"Evgeniou","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2018.8645435"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1131"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2019.00524"},{"key":"ref27","first-page":"153","article-title":"Multi-task Gaussian process prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Bonilla","year":"2007"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2538028"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref31","first-page":"737","article-title":"Multi-task learning via conic programming","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kato","year":"2007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"ref36","first-page":"1","article-title":"Spectral networks and locally connected networks on graphs","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Bruna","year":"2014"},{"key":"ref37","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Defferrard","year":"2016"},{"key":"ref38","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Welling","year":"2016"},{"key":"ref39","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"ref40","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hamilton","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ddtec.2020.11.009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220077"},{"key":"ref46","first-page":"5171","article-title":"Link prediction based on graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zhang","year":"2018"},{"key":"ref47","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer","year":"2017"},{"key":"ref48","first-page":"1","article-title":"How powerful are graph neural networks?","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Xu","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413523"},{"key":"ref50","first-page":"5241","article-title":"GMNN: Graph Markov neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qu","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1561\/2200000013"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5014-9_12"},{"key":"ref53","first-page":"1","article-title":"Auto-encoding variational bayes","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"issue":"36, pp. 517-522","key":"ref54","article-title":"Amortized inference in probabilistic reasoning","volume-title":"Proc. Annu. Meeting Cogn. Sci. Soc.","volume":"36","author":"Gershman","year":"2014"},{"key":"ref55","first-page":"1","article-title":"Neural structured prediction for inductive node classification","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Qu","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2016.2591526"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1186\/s40535-016-0018-x"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511969"},{"key":"ref59","first-page":"1411","article-title":"BaCaDI: Bayesian causal discovery with unknown interventions","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"H\u00e4gele","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref61","first-page":"9492","article-title":"DAGs with NO TEARS: Continuous optimization for structure learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zheng","year":"2018"},{"key":"ref62","first-page":"1","article-title":"Causal discovery with reinforcement learning","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Zhu","year":"2020"},{"key":"ref63","first-page":"1501","article-title":"CASTLE: Regularization via auxiliary causal graph discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kyono","year":"2020"},{"key":"ref64","first-page":"7095","article-title":"BCD Nets: Scalable variational approaches for Bayesian causal discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cundy","year":"2021"},{"key":"ref65","first-page":"17943","article-title":"On the role of sparsity and DAG constraints for learning linear DAGs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ng","year":"2020"},{"issue":"89","key":"ref66","first-page":"1","article-title":"Causal discovery from heterogeneous\/nonstationary data","volume":"21","author":"Huang","year":"2020","journal-title":"J. Mach. Learn. Res."},{"article-title":"Exploration on deep drug discovery: Representation and learning","year":"2018","author":"Liu","key":"ref67"},{"key":"ref68","first-page":"1","article-title":"A tutorial on energy-based learning","volume":"1","author":"LeCun","year":"2006","journal-title":"Predicting Structured Data"},{"issue":"9","key":"ref69","first-page":"1453","article-title":"Large margin methods for structured and interdependent output variables","volume":"6","author":"Tsochantaridis","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390268"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.09.023"},{"key":"ref72","first-page":"1","article-title":"Generalized energy based models","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Arbel","year":"2021"},{"volume-title":"Causal Inference in Statistics: A Primer","year":"2016","author":"Glymour","key":"ref73"},{"key":"ref74","first-page":"1","article-title":"Fast and accurate deep network learning by exponential linear units (ELUS)","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Clevert","year":"2016"},{"article-title":"Learning energy-based model with flow-based backbone by neural transport MCMC","year":"2020","author":"Nijkamp","key":"ref75"},{"key":"ref76","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist., Workshop Conf. Proc.","author":"Gutmann","year":"2010"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"ref78","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1984.4767596"},{"key":"ref80","first-page":"7154","article-title":"DAG-GNN: DAG structure learning with graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2019"},{"key":"ref81","first-page":"9551","article-title":"Causal discovery from soft interventions with unknown targets: Characterization and learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Jaber","year":"2020"},{"key":"ref82","first-page":"1039","article-title":"Permutation-based causal structure learning with unknown intervention targets","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Squires","year":"2020"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/0378-8733(83)90021-7"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956823"},{"key":"ref85","first-page":"83","article-title":"Task clustering and gating for Bayesian multitask learning","volume":"4","author":"Bakker","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1075"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2012.03.014"},{"key":"ref88","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall","year":"2018"},{"key":"ref89","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2018"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019977"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref93","first-page":"1","article-title":"On the bottleneck of graph neural networks and its practical implications","volume-title":"Proc. J. Int. Conf. Learn. Representations","author":"Alon","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11164900.pdf?arnumber=11164900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:07:30Z","timestamp":1764839250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":93,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3610096","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}