{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:51:43Z","timestamp":1780501903972,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of Hong Kong Special Administrative Region, China","award":["PolyU 25206422"],"award-info":[{"award-number":["PolyU 25206422"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406269"],"award-info":[{"award-number":["62406269"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Committee of The Hong Kong Polytechnic University","award":["RKB0"],"award-info":[{"award-number":["RKB0"]}]},{"name":"Research Committee of The Hong Kong Polytechnic University","award":["G-UARJ"],"award-info":[{"award-number":["G-UARJ"]}]},{"name":"NSFC\/Research Grants Council (RGC) Joint Research Scheme","award":["N_HKBU214\/21"],"award-info":[{"award-number":["N_HKBU214\/21"]}]},{"name":"Seed Funding for Collaborative Research Grants of Hong Kong Baptist University","award":["RC-SFCRG\/23-24\/R2\/SCI\/10"],"award-info":[{"award-number":["RC-SFCRG\/23-24\/R2\/SCI\/10"]}]},{"name":"Guangdong and Hong Kong Universities \u201c1 + 1 + 1\u201d Cross-Campus Research Collaboration Scheme","award":["2025A0505000004"],"award-info":[{"award-number":["2025A0505000004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tsmc.2025.3646993","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:40:50Z","timestamp":1768423250000},"page":"1895-1910","source":"Crossref","is-referenced-by-count":1,"title":["Causality-Informed Neural Networks for Regularized Learning in Regression Problems"],"prefix":"10.1109","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6831-3175","authenticated-orcid":false,"given":"Xiaoge","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-8100","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0100-8154","authenticated-orcid":false,"given":"Xiao-Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"Business School, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng-Lei","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Data Science, Frontier of Artificial Networks (FAN) Laboratory, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7629-4648","authenticated-orcid":false,"given":"Yiu-Ming","family":"Cheung","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5737-966X","authenticated-orcid":false,"given":"Indranil","family":"Bose","sequence":"additional","affiliation":[{"name":"NEOMA Business School, Reims, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3185102"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3530399"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3170071"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3427345"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3321746"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2025.3526137"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1088\/3050-2454\/adcef2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/biom.13612"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2022.113800"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2024.114305"},{"key":"ref13","article-title":"Visualizing deep neural network decisions: Prediction difference analysis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zintgraf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3468010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3519608"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00175"},{"key":"ref17","first-page":"8346","article-title":"An investigation of why overparameterization exacerbates spurious correlations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sagawa"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3361689"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-49817-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3365968"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2836958"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/msom.2024.1061"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3537832"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671551"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02902-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3241036"},{"key":"ref28","first-page":"10676","article-title":"Matching learned causal effects of neural networks with domain priors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kancheti"},{"key":"ref29","first-page":"1501","article-title":"CASTLE: Regularization via auxiliary causal graph discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kyono"},{"key":"ref30","first-page":"86","article-title":"Incorporating causal graphical prior knowledge into predictive modeling via simple data augmentation","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Teshima"},{"issue":"36","key":"ref31","first-page":"1","article-title":"Invariant models for causal transfer learning","volume":"19","author":"Rojas-Carulla","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref32","first-page":"459","article-title":"On causal and anticausal learning","volume-title":"Proc. 29th Int. Conf. Int. Conf. Mach. Learn.","author":"Janzing"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.14"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2024.0891"},{"key":"ref35","first-page":"9472","article-title":"DAGs with NO TEARS: Continuous optimization for structure learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zheng"},{"key":"ref36","first-page":"3414","article-title":"Learning sparse nonparametric DAGs","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Zheng"},{"key":"ref37","volume-title":"Causality: Models, Reasoning and Inference","volume":"19","author":"Pearl","year":"2000"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1085"},{"issue":"1","key":"ref39","first-page":"3065","article-title":"High-dimensional learning of linear causal networks via inverse covariance estimation","volume":"15","author":"Loh","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/b98874"},{"key":"ref41","first-page":"656","article-title":"Avoiding discrimination through causal reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kilbertus"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3233\/faia230495"},{"key":"ref43","first-page":"24934","article-title":"Debiasing graph neural networks via learning disentangled causal substructure","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref44","first-page":"11450","article-title":"Improving multi-task generalization via regularizing spurious correlation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009730122752"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3079836"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref48","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref49","volume-title":"UCI Machine Learning Repository","author":"Asuncion","year":"2007"},{"key":"ref50","first-page":"804","article-title":"Kernel-based conditional independence test and application in causal discovery","volume-title":"Proc. 27th Conf. Uncertainty Artif. Intell.","author":"Zhang"},{"key":"ref51","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"issue":"1","key":"ref52","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00082"},{"key":"ref58","volume-title":"Towards Causally-Aware Machine Learning","author":"Kyono","year":"2021"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11406734\/11353218.pdf?arnumber=11353218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:58:37Z","timestamp":1771966717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":58,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3646993","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}