{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T10:18:00Z","timestamp":1778408280580,"version":"3.51.4"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001852","name":"Indo-French Centre for the Promotion of Advanced Research","doi-asserted-by":"publisher","award":["CSRP 6702-2"],"award-info":[{"award-number":["CSRP 6702-2"]}],"id":[{"id":"10.13039\/501100001852","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":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3594360","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T18:31:16Z","timestamp":1753986676000},"page":"10022-10032","source":"Crossref","is-referenced-by-count":2,"title":["SEMI-CAVA: A Causal Variational Approach to Semi-Supervised Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7178-8646","authenticated-orcid":false,"given":"Saptarshi","family":"Saha","sequence":"first","affiliation":[{"name":"Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5471-5398","authenticated-orcid":false,"given":"Pratyush Kumar","family":"Sahoo","sequence":"additional","affiliation":[{"name":"Indian Statistical Institute, Kolkata, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7207-5018","authenticated-orcid":false,"given":"Utpal","family":"Garain","sequence":"additional","affiliation":[{"name":"Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"459","article-title":"On causal and anticausal learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sch\u00f6lkopf","year":"2012"},{"key":"ref2","first-page":"1","article-title":"Semi-supervised learning, causality, and the conditional cluster assumption","volume-title":"Proc. 36th Int. Conf. Uncertainty Artif. Intell.","volume":"124","author":"K\u00fcgelgen","year":"2020"},{"key":"ref3","first-page":"16121","article-title":"On non-random missing labels in semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01959"},{"key":"ref5","first-page":"857","article-title":"Deep structural causal models for tractable counterfactual inference","volume":"33","author":"Pawlowski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref6","first-page":"289","article-title":"A causal view on robustness of neural networks","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"ref8","first-page":"6449","article-title":"Causal effect inference with deep latent-variable models","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst., ser. NIPS\u201917","author":"Louizos","year":"2017"},{"key":"ref9","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref11","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot","year":"2019"},{"key":"ref12","article-title":"Pseudo-label : The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. ICML 2013 Workshop: Challenges Representation Learn.","author":"Lee","year":"2013"},{"key":"ref13","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30: Annu. Conf. Neural Inf. Process. Syst.","author":"Tarvainen","year":"2017"},{"key":"ref14","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Xie","year":"2020"},{"key":"ref15","article-title":"Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Berthelot","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01407"},{"key":"ref18","first-page":"18613","article-title":"Randaugment: Practical automated data augmentation with a reduced search space","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cubuk","year":"2020"},{"key":"ref19","article-title":"Improved regularization of convolutional neural networks with cutout","volume-title":"CoRR","volume":"abs\/1708.04552","author":"Devries","year":"2017"},{"key":"ref20","article-title":"Selfmatch: Combining contrastive selfsupervision and consistency for semi-supervised learning","author":"Kim","year":"2021"},{"key":"ref21","first-page":"18408","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang","year":"2021"},{"key":"ref22","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","volume":"2","author":"Kingma","year":"2014"},{"key":"ref23","article-title":"DIVA: Domain invariant variational autoencoder","author":"Ilse","year":"2019"},{"key":"ref24","article-title":"The variational fair autoencoder","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Louizos","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015885"},{"key":"ref26","first-page":"708","article-title":"Learning disentangled joint continuous anddiscrete representations","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst., ser. NIPS\u201918","author":"Dupont","year":"2018"},{"issue":"8","key":"ref27","first-page":"7413","article-title":"SHOT-VAE: Semi-supervised deep generative models with label-aware ELBO approximations","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"35","author":"Feng","year":"2021"},{"key":"ref28","article-title":"Adversarial robustness through the lens of causality","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2022"},{"key":"ref29","article-title":"Counterfactual generative networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Axel Sauer","year":"2021"},{"key":"ref30","article-title":"Explaining visual counterfactual explainers","volume-title":"Trans. Mach. Learn. Res.","author":"Velazquez","year":"2023"},{"key":"ref31","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"issue":"2","key":"ref32","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","volume":"32","author":"Rezende","year":"2014"},{"key":"ref33","article-title":"When does label smoothing help?","volume-title":"Proc. 33 rd Int. Conf. Neural Inf. Process. Syst.","author":"M\u00fcller","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1561\/2400000052"},{"key":"ref35","first-page":"16451","article-title":"Self-supervised learning with data augmentations provably isolates content from style","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"K\u00fcgelgen","year":"2021"},{"key":"ref36","first-page":"4555","article-title":"Selecting data augmentation for simulating interventions","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Ilse","year":"2021"},{"key":"ref37","first-page":"12943","article-title":"Consistency regularization for variational auto-encoders","volume":"34","author":"Sinha","year":"2021","journal-title":"Neural Inf. Process. Syst."},{"issue":"06","key":"ref38","first-page":"10093","article-title":"A calculus for stochastic interventions:causal effect identification and surrogate experiments","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"34","author":"Correa","year":"2020"},{"key":"ref39","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref40","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS Workshop Deep Learn. Unsupervised Feature Learn.","author":"Netzer","year":"2011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8"},{"key":"ref42","article-title":"The liver tumor segmentation benchmark (LiTS)","volume-title":"Med. Image Anal.","volume":"84","author":"Bilic","year":"2023"},{"key":"ref43","article-title":"Don\u2019t fear the unlabelled: Safe semi-supervised learning via debiasing","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Schmutz","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.105474"},{"issue":"5","key":"ref45","first-page":"1122","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume-title":"Cell","volume":"172","author":"Kermany","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.161"},{"key":"ref47","article-title":"Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (ISIC)","author":"Codella","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863"},{"key":"ref49","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Laine","year":"2017"},{"key":"ref50","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Sohn","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01485"},{"issue":"57","key":"ref52","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume-title":"J. Mach. Learn. Res.","volume":"22","author":"Papamakarios","year":"2021"},{"key":"ref53","first-page":"12979","article-title":"Contrastive learning inverts the data generating process","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zimmermann","year":"2021"},{"key":"ref54","article-title":"Falcon and the PyTorch lightning team","volume-title":"PyTorch Lightning","year":"2019"},{"key":"ref55","article-title":"Categorical reparameterization with Gumbel-softmax","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref56","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Higgins","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00081"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11105572.pdf?arnumber=11105572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:59Z","timestamp":1759772219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11105572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":58,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3594360","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}