{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T02:48:42Z","timestamp":1773888522542,"version":"3.50.1"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["12320101001"],"award-info":[{"award-number":["12320101001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>Disentangled representation learning aims to learn low-dimensional representations where each dimension corresponds to an underlying generative factor. While the Variational Auto-Encoder (VAE) is widely used for this purpose, most existing methods assume independence among factors, a simplification that does not hold in many real-world scenarios where factors are often interdependent and exhibit causal relationships. To overcome this limitation, we propose the Disentangled Causal Variational Auto-Encoder (DCVAE), a novel supervised VAE framework that integrates causal flows into the representation learning process, enabling the learning of more meaningful and interpretable disentangled representations. We evaluate DCVAE on both synthetic and real-world datasets, demonstrating its superior ability in causal disentanglement and intervention experiments. Furthermore, DCVAE outperforms state-of-the-art methods in various downstream tasks, highlighting its potential for learning true causal structures among factors.<\/jats:p>","DOI":"10.1145\/3748660","type":"journal-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T19:54:27Z","timestamp":1752522867000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Causal Flow-Based Variational Auto-Encoder for Disentangled Causal Representation Learning"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6357-7849","authenticated-orcid":false,"given":"Di","family":"Fan","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3100-1570","authenticated-orcid":false,"given":"Yannian","family":"Kou","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9030-2042","authenticated-orcid":false,"given":"Chuanhou","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,18]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230258"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11867"},{"key":"e_1_3_1_5_2","unstructured":"Christopher P. Burgess Irina Higgins Arka Pal Loic Matthey Nick Watters Guillaume Desjardins and Alexander Lerchner. 2018. Understanding disentangling in \\(\\beta\\) -VAE. arXiv:1804.03599. Retrieved from https:\/\/arxiv.org\/abs\/1804.03599"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112079"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04167-0"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532011"},{"key":"e_1_3_1_9_2","first-page":"2359","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Connor Marissa","year":"2021","unstructured":"Marissa Connor, Gregory Canal, and Christopher Rozell. 2021. Variational autoencoder with learned latent structure. In International Conference on Artificial Intelligence and Statistics. PMLR, 2359\u20132367."},{"key":"e_1_3_1_10_2","article-title":"Learning disentangled joint continuous and discrete representations","volume":"31","author":"Dupont Emilien","year":"2018","unstructured":"Emilien Dupont. 2018. Learning disentangled joint continuous and discrete representations. In Advances in Neural Information Processing Systems, Vol. 31.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_11_2","volume-title":"International Conference on Learning Representations","author":"Eastwood Cian","year":"2018","unstructured":"Cian Eastwood and Christopher K. I. Williams. 2018. A framework for the quantitative evaluation of disentangled representations. In International Conference on Learning Representations."},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570509"},{"key":"e_1_3_1_13_2","first-page":"1414","volume-title":"International Conference on Machine Learning","author":"Hartford Jason","year":"2017","unstructured":"Jason Hartford, Greg Lewis, Kevin Leyton-Brown, and Matt Taddy. 2017. Deep IV: A flexible approach for counterfactual prediction. In International Conference on Machine Learning. PMLR, 1414\u20131423."},{"key":"e_1_3_1_14_2","volume-title":"International Conference on Learning Representations","author":"He Jiawei","year":"2018","unstructured":"Jiawei He, Yu Gong, Joseph Marino, Greg Mori, and Andreas Lehrmann. 2018. Variational autoencoders with jointly optimized latent dependency structure. In International Conference on Learning Representations."},{"key":"e_1_3_1_15_2","volume-title":"International Conference on Learning Representations","author":"Higgins Irina","unstructured":"Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. Beta-VAE: Learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations."},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367243.3367388"},{"key":"e_1_3_1_17_2","first-page":"2078","volume-title":"International Conference on Machine Learning","author":"Huang Chin-Wei","year":"2018","unstructured":"Chin-Wei Huang, David Krueger, Alexandre Lacoste, and Aaron Courville. 2018. Neural autoregressive flows. In International Conference on Machine Learning. PMLR, 2078\u20132087."},{"key":"e_1_3_1_18_2","article-title":"Unsupervised feature extraction by time-contrastive learning and nonlinear ICA","volume":"29","author":"Hyvarinen Aapo","year":"2016","unstructured":"Aapo Hyvarinen and Hiroshi Morioka. 2016. Unsupervised feature extraction by time-contrastive learning and nonlinear ICA. In Advances in Neural Information Processing Systems, Vol. 29.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106107"},{"key":"e_1_3_1_20_2","first-page":"2207","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Khemakhem Ilyes","year":"2020","unstructured":"Ilyes Khemakhem, Diederik Kingma, Ricardo Monti, and Aapo Hyvarinen. 2020. Variational autoencoders and nonlinear ICA: A unifying framework. In International Conference on Artificial Intelligence and Statistics. PMLR, 2207\u20132217."},{"key":"e_1_3_1_21_2","first-page":"3520","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Khemakhem Ilyes","year":"2021","unstructured":"Ilyes Khemakhem, Ricardo Monti, Robert Leech, and Aapo Hyvarinen. 2021. Causal autoregressive flows. In International Conference on Artificial Intelligence and Statistics. PMLR, 3520\u20133528."},{"key":"e_1_3_1_22_2","unstructured":"Bo-Kyeong Kim Sungjin Park Geonmin Kim and Soo-Young Lee. 2020. Semi-supervised disentanglement with independent vector variational autoencoders. arXiv:2003.06581. Retrieved from https:\/\/arxiv.org\/abs\/2003.06581"},{"key":"e_1_3_1_23_2","first-page":"2649","volume-title":"International Conference on Machine Learning","author":"Kim Hyunjik","year":"2018","unstructured":"Hyunjik Kim and Andriy Mnih. 2018. Disentangling by factorising. In International Conference on Machine Learning. PMLR, 2649\u20132658."},{"key":"e_1_3_1_24_2","unstructured":"Minyoung Kim Yuting Wang Pritish Sahu and Vladimir Pavlovic. 2019. Relevance factor VAE: Learning and identifying disentangled factors. arXiv:1902.01568. Retrieved from https:\/\/arxiv.org\/abs\/1902.01568"},{"key":"e_1_3_1_25_2","article-title":"Improved variational inference with inverse autoregressive flow","volume":"29","author":"Kingma Durk P.","year":"2016","unstructured":"Durk P. Kingma, Tim Salimans, Rafal Jozefowicz, Xi Chen, Ilya Sutskever, and Max Welling. 2016. Improved variational inference with inverse autoregressive flow. In Advances in Neural Information Processing Systems, Vol. 29.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_26_2","volume-title":"International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational bayes. In International Conference on Learning Representations."},{"key":"e_1_3_1_27_2","volume-title":"International Conference on Learning Representations","author":"Kocaoglu Murat","year":"2018","unstructured":"Murat Kocaoglu, Christopher Snyder, Alexandros, G. Dimakis, and Sriram Vishwanath. 2018. CausalGAN: Learning causal implicit generative models with adversarial training. In International Conference on Learning Representations."},{"key":"e_1_3_1_28_2","volume-title":"International Conference on Learning Representations","author":"Kumar Abhishek","year":"2018","unstructured":"Abhishek Kumar, Prasanna Sattigeri, and Avinash Balakrishnan. 2018. Variational inference of disentangled latent concepts from unlabeled observations. In International Conference on Learning Representations."},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3552487.3556435"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_1_31_2","first-page":"4114","volume-title":"International Conference on Machine Learning","author":"Locatello Francesco","year":"2019","unstructured":"Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Raetsch, Sylvain Gelly, Bernhard Sch\u00f6lkopf, and Olivier Bachem. 2019. Challenging common assumptions in the unsupervised learning of disentangled representations. In International Conference on Machine Learning. PMLR, 4114\u20134124."},{"key":"e_1_3_1_32_2","first-page":"6348","volume-title":"International Conference on Machine Learning","author":"Locatello Francesco","year":"2020","unstructured":"Francesco Locatello, Ben Poole, Gunnar R\u00e4tsch, Bernhard Sch\u00f6lkopf, Olivier Bachem, and Michael Tschannen. 2020. Weakly-supervised disentanglement without compromises. In International Conference on Machine Learning. PMLR, 6348\u20136359."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3464304"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/3546258.3546315"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"e_1_3_1_36_2","unstructured":"Judea Pearl. 2000. Models Reasoning and Inference Vol. 19. Cambridge University Press Cambridge."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20781"},{"key":"e_1_3_1_38_2","first-page":"1530","volume-title":"International Conference on Machine Learning","author":"Rezende Danilo","year":"2015","unstructured":"Danilo Rezende and Shakir Mohamed. 2015. Variational inference with normalizing flows. In International Conference on Machine Learning. PMLR, 1530\u20131538."},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Bernhard Sch\u00f6lkopf. 2022. Causality for machine learning. In Probabilistic and Causal Inference: The Works of Judea Pearl. Hector Geffner Rina Dechter and Joseph Y. Halpern (Eds.) 765\u2013804.","DOI":"10.1145\/3501714.3501755"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1899412.1899415"},{"key":"e_1_3_1_41_2","first-page":"1","article-title":"Weakly supervised disentangled generative causal representation learning","volume":"23","author":"Shen Xinwei","year":"2022","unstructured":"Xinwei Shen, Furui Liu, Hanze Dong, Qing Lian, Zhitang Chen, and Tong Zhang. 2022. Weakly supervised disentangled generative causal representation learning. Journal of Machine Learning Research 23 (2022), 1\u201355.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_42_2","unstructured":"Rui Shu Yining Chen Abhishek Kumar Stefano Ermon and Ben Poole. 2019. Weakly supervised disentanglement with guarantees. arXiv:1910.09772. Retrieved from https:\/\/arxiv.org\/abs\/1910.09772"},{"key":"e_1_3_1_43_2","article-title":"Ladder variational autoencoders","volume":"29","author":"S\u00f8nderby Casper Kaae","year":"2016","unstructured":"Casper Kaae S\u00f8nderby, Tapani Raiko, Lars Maal\u00f8e, S\u00f8ren Kaae S\u00f8nderby, and Ole Winther. 2016. Ladder variational autoencoders. In Advances in Neural Information Processing Systems, Vol. 29.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_44_2","volume-title":"Causation, Prediction, and Search","author":"Spirtes Peter","year":"2000","unstructured":"Peter Spirtes, Clark N. Glymour, and Richard Scheines. 2000. Causation, Prediction, and Search. MIT Press."},{"key":"e_1_3_1_45_2","first-page":"32540","volume-title":"International Conference on Machine Learning","author":"Squires Chandler","year":"2023","unstructured":"Chandler Squires, Anna Seigal, Salil S. Bhate, and Caroline Uhler. 2023. Linear causal disentanglement via interventions. In International Conference on Machine Learning. PMLR, 32540\u201332560."},{"key":"e_1_3_1_46_2","first-page":"6056","volume-title":"International Conference on Machine Learning","author":"Suter Raphael","year":"2019","unstructured":"Raphael Suter, Djordje Miladinovic, Bernhard Sch\u00f6lkopf, and Stefan Bauer. 2019. Robustly disentangled causal mechanisms: Validating deep representations for interventional robustness. In International Conference on Machine Learning. PMLR, 6056\u20136065."},{"key":"e_1_3_1_47_2","first-page":"10401","volume-title":"International Conference on Machine Learning","author":"Tr\u00e4uble Frederik","year":"2021","unstructured":"Frederik Tr\u00e4uble, Elliot Creager, Niki Kilbertus, Francesco Locatello, Andrea Dittadi, Anirudh Goyal, Bernhard Sch\u00f6lkopf, and Stefan Bauer. 2021. On disentangled representations learned from correlated data. In International Conference on Machine Learning. PMLR, 10401\u201310412."},{"key":"e_1_3_1_48_2","first-page":"37","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Wehenkel Antoine","year":"2021","unstructured":"Antoine Wehenkel and Gilles Louppe. 2021. Graphical normalizing flows. In International Conference on Artificial Intelligence and Statistics. PMLR, 37\u201345."},{"key":"e_1_3_1_49_2","unstructured":"Yijun Xiao and William Yang Wang. 2019. Disentangled representation learning with Wasserstein total correlation. arXiv:1912.12818. Retrieved from https:\/\/arxiv.org\/abs\/1912.12818"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26266"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"issue":"2","key":"e_1_3_1_52_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3470659","article-title":"Hybrid variational autoencoder for recommender systems","volume":"16","author":"Zhang Hangbin","year":"2021","unstructured":"Hangbin Zhang, Raymond K. Wong, and Victor W. Chu. 2021. Hybrid variational autoencoder for recommender systems. ACM Transactions on Knowledge Discovery from Data 16, 2 (2021), 1\u201337.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Ziyu Zhao Anpeng Wu Kun Kuang Ruoxuan Xiong Bo Li Zhihua Wang and Fei Wu. 2024. Networked instrumental variable for treatment effect estimation with unobserved confounders. IEEE Transactions on Knowledge and Data Engineering 37 2 (2025) 823\u2013836.","DOI":"10.1109\/TKDE.2024.3491776"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:03:22Z","timestamp":1758215002000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748660"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,18]]},"references-count":52,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3748660"],"URL":"https:\/\/doi.org\/10.1145\/3748660","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,18]]},"assertion":[{"value":"2024-12-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}