{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T20:40:56Z","timestamp":1782938456368,"version":"3.54.5"},"reference-count":199,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tai.2025.3646958","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:45:27Z","timestamp":1766429127000},"page":"3634-3652","source":"Crossref","is-referenced-by-count":1,"title":["Emerging Synergies in Causality and Deep Generative Models: A Survey"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1305-2622","authenticated-orcid":false,"given":"Guanglin","family":"Zhou","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1003-7459","authenticated-orcid":false,"given":"Shaoan","family":"Xie","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4740-6254","authenticated-orcid":false,"given":"Guang-Yuan","family":"Hao","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9633-3392","authenticated-orcid":false,"given":"Shiming","family":"Chen","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5867-7254","authenticated-orcid":false,"given":"Biwei","family":"Huang","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2273-1862","authenticated-orcid":false,"given":"Xiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"CSIRO’s Data61, Eveleigh, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3119-4763","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"CSIRO’s Data61, Eveleigh, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5839-3765","authenticated-orcid":false,"given":"Liming","family":"Zhu","sequence":"additional","affiliation":[{"name":"CSIRO’s Data61, Eveleigh, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4149-839X","authenticated-orcid":false,"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0738-9958","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref2","article-title":"Generative adversarial nets","volume-title":"Proc. NIPS","author":"Goodfellow","year":"2014"},{"key":"ref3","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations (ICLR), Banff, AB, Canada","author":"Kingma","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref5","article-title":"Modeling the data-generating process is necessary for out-of-distribution generalization","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kaur","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614823"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3648609"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref11","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref12","first-page":"16451","article-title":"Self-supervised learning with data augmentations provably isolates content from style","volume":"34","author":"Von K\u00fcgelgen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref13","article-title":"Conditional generative adversarial nets","volume":"2014","author":"Mirza"},{"key":"ref14","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. NIPS","author":"Chen","year":"2016"},{"key":"ref15","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins","year":"2016"},{"key":"ref16","article-title":"Density estimation using real NVP","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","year":"2017"},{"key":"ref17","article-title":"GLOW: Generative flow with invertible 1x1 convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref19","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116668"},{"key":"ref21","first-page":"289","article-title":"A causal view on robustness of neural networks","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","article-title":"Causal machine learning: A survey and open problems","author":"Kaddour","year":"2022"},{"key":"ref23","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","author":"Pearl","year":"1988"},{"key":"ref24","volume-title":"The Book of Why: The New Science of Cause and Effect.","author":"Pearl","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00140-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2019.00524"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2026.103478"},{"key":"ref28","article-title":"Deep structural causal models for tractable counterfactual inference","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Pawlowski","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4135\/9781412952637.n77"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISACV.2018.8354080"},{"key":"ref31","article-title":"A comprehensive survey and analysis of generative models in machine learning","volume":"38","author":"Harshvardhan","year":"2020","journal-title":"Comput. Sci. Rev."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116668"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref34","article-title":"Causal representation learning (CRL) workshop at NeurIPS 2023.","year":"2023"},{"key":"ref35","article-title":"Causal representation learning workshop at NeurIPS 2024.","year":"2024"},{"key":"ref36","article-title":"Causcien: Uncovering causality in science workshop at NeurIPS 2025.","year":"2025"},{"key":"ref37","article-title":"Causality in vision workshop at CVPR 2021.","year":"2021"},{"key":"ref38","article-title":"Causality in vision workshop at ECCV 2022.","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1754.001.0001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref41","article-title":"From statistical to causal learning","author":"Scholkopf","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3501714.3501743"},{"key":"ref43","article-title":"Constructing Bayesian network models of gene expression networks from microarray data","author":"Spirtes","year":"2000"},{"issue":"10","key":"ref44","first-page":"2003","article-title":"A linear non-Gaussian acyclic model for causal discovery","volume":"7","author":"Shimizu","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/11893295_45"},{"key":"ref46","article-title":"On the identifiability of the post-nonlinear causal model","author":"Zhang","year":"2012"},{"key":"ref47","article-title":"Variational autoencoders and nonlinear ICA: A unifying framework","author":"Khemakhem","year":"2020"},{"key":"ref48","article-title":"Identifying through flows for recovering latent representations","author":"Li","year":"2019"},{"key":"ref49","first-page":"2641","article-title":"Covariate-informed representation learning to prevent posterior collapse of IVAE","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kim","year":"2023"},{"key":"ref50","article-title":"Multi-domain image generation and translation with identifiability guarantees","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Xie","year":"2023"},{"key":"ref51","first-page":"11455","article-title":"Partial disentanglement for domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kong","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06221-2"},{"key":"ref53","article-title":"Improving language understanding by generative pretraining","author":"Radford","year":"2018"},{"key":"ref54","first-page":"24963","article-title":"Diffusion based representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mittal","year":"2023"},{"issue":"8","key":"ref55","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref56","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref57","volume-title":"Gpt-4 Technical Report","year":"2023"},{"key":"ref58","article-title":"Llama open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref59","article-title":"Gemini a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref60","volume-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref61","article-title":"CausalGAN: Learning causal implicit generative models with adversarial training","author":"Kocaoglu","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref63","article-title":"Counterfactual generative networks","author":"Sauer","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00922"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref67","article-title":"Causal-TGAN: Causally-aware synthetic tabular data generative adversarial network","author":"Wen","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/201"},{"key":"ref69","article-title":"DECAF: Generating fair synthetic data using causally-aware generative networks","volume-title":"Proc. NeurIPS","author":"van Breugel","year":"2021"},{"key":"ref70","article-title":"UCI machine learning repository, University of California, Irvine, School of Information and Computer Sciences","author":"Asuncion","year":"2007"},{"key":"ref71","first-page":"1","article-title":"Weakly supervised disentangled generative causal representation learning","volume":"23","author":"Shen","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00394"},{"key":"ref74","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume-title":"Proc. NeurIPS","author":"Barbu","year":"2019"},{"key":"ref75","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref76","first-page":"5389","article-title":"Do ImageNet classifiers generalize to imagenet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht","year":"2019"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_75"},{"key":"ref81","article-title":"High fidelity image counterfactuals with probabilistic causal models","author":"Ribeiro","year":"2023"},{"issue":"178","key":"ref82","first-page":"1","article-title":"Morpho-MNIST: quantitative assessment and diagnostics for representation learning","volume":"20","author":"Castro","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001779"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref85","article-title":"A causal lens for controllable text generation","volume-title":"Proc. NeurIPS","author":"Hu","year":"2021"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287572"},{"key":"ref87","article-title":"Diffusion causal models for counterfactual estimation","volume-title":"Proc. CLeaR","author":"Sanchez","year":"2022"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref89","article-title":"\"What is healthy? Generative counterfactual diffusion for lesion localization,\" MICCAI workshop on deep generative models. Cham: Springer Nature Switzerland","author":"Sanchez","year":"2022"},{"key":"ref90","article-title":"Identifying the best machine learning algorithms for brain tumor segmentationprogression assessmentand overall survival prediction in the brats challenge","author":"Bakas","year":"2018"},{"key":"ref91","article-title":"Conditional independence testing using generative adversarial networks","volume":"32","author":"Bellot","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1038\/nature11005"},{"issue":"1","key":"ref93","first-page":"9831","article-title":"Structural agnostic modeling: Adversarial learning of causal graphs","volume":"23","author":"Kalainathan","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1126\/science.1105809"},{"key":"ref95","article-title":"GANITE: Estimation of individualized treatment effects using generative adversarial nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yoon","year":"2018"},{"key":"ref96","first-page":"3076","article-title":"Estimating individual treatment effect: generalization bounds and algorithms","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Shalit","year":"2017"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2004.04.011"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS-D-14-00034.1"},{"key":"ref99","first-page":"16434","article-title":"Estimating the effects of continuous-valued interventions using generative adversarial networks","volume":"33","author":"Bica","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2764"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6014"},{"issue":"1","key":"ref102","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2016.35","article-title":"Mimic-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"ref103","article-title":"VACA: Design of variational graph autoencoders for interventional and counterfactual queries","author":"S\u00e1nchez-Mart\u00edn","year":"2021"},{"key":"ref104","first-page":"3520","article-title":"Causal autoregressive flows","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Khemakhem","year":"2021"},{"issue":"1","key":"ref105","first-page":"1103","article-title":"Distinguishing cause from effect using observational data: methods and benchmarks","volume":"17","author":"Mooij","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2004.827088"},{"key":"ref107","article-title":"OCDAF: Ordered causal discovery with autoregressive flows","author":"Kamkari","year":"2023"},{"key":"ref108","article-title":"Counterfactual (non-) identifiability of learned structural causal models","author":"Nasr-Esfahany","year":"2023"},{"key":"ref109","article-title":"Diffusion models for causal discovery via topological ordering","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Sanchez","year":"2023"},{"key":"ref110","article-title":"Interventional and counterfactual inference with diffusion models","author":"Chao","year":"2023"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00595-y"},{"key":"ref112","article-title":"Investigating causal understanding in LLMs","volume-title":"Proc. NeurIPS ML Safety Workshop","author":"Hobbhahn","year":"2022"},{"key":"ref113","article-title":"Understanding causality with large language models Feasibility and opportunities","author":"Zhang","year":"2023"},{"key":"ref114","article-title":"Answering causal questions with augmented LLMs","author":"Pawlowski","year":"2023"},{"key":"ref115","article-title":"Causal reasoning and large language models: Opening a new frontier for causality","author":"Kiciman","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref116","article-title":"Neuropathic pain diagnosis simulator for causal discovery algorithm evaluation","volume":"32","author":"Tu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.743"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.33"},{"key":"ref119","article-title":"Choice of plausible alternatives: An evaluation of commonsense causal reasoning","volume-title":"Proc. AAAI Spring Symp. Ser.","author":"Roemmele","year":"2011"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2711"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-0702"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.60"},{"key":"ref123","article-title":"LMPRIORS: Pre-trained language models as task-specific priors","author":"Choi","year":"2022"},{"key":"ref124","article-title":"Can large language models build causal graphs?","author":"Long","year":"2023"},{"key":"ref125","article-title":"From query tools to causal architects: Harnessing large language models for advanced causal discovery from data","author":"Ban","year":"2023"},{"key":"ref126","article-title":"Causal discovery with language models as imperfect experts","volume-title":"Proc. Workshop Structured Probabilistic Inference & Generative Model. (ICML)","author":"Long","year":"2023"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1988.tb01721.x"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970043"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007421730016"},{"key":"ref130","article-title":"Causal parrots: Large language models may talk causality but are not causal","author":"Willig","year":"2023"},{"key":"ref131","article-title":"Can large language models infer causation from correlation?","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Jin","year":"2024"},{"key":"ref132","article-title":"CLadder: A benchmark to assess causal reasoning capabilities of language models","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Jin","year":"2023"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16833"},{"key":"ref134","article-title":"MolGAN: An implicit generative model for small molecular graphs","author":"De Cao","year":"2018"},{"key":"ref135","first-page":"1462","article-title":"DRAW: A recurrent neural network for image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gregor","year":"2015"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00818"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref138","article-title":"Adversarial feature learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Donahue","year":"2017"},{"key":"ref139","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. ICLR","author":"Higgins","year":"2017"},{"key":"ref140","first-page":"859","article-title":"Nonlinear ICA using auxiliary variables and generalized contrastive learning","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Hyvarinen","year":"2019"},{"key":"ref141","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Locatello","year":"2019"},{"key":"ref142","article-title":"Counterfactuals uncover the modular structure of deep generative models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Besserve","year":"2020"},{"key":"ref143","article-title":"On causal and anticausal learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sch\u00f6lkopf","year":"2012"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref145","first-page":"2207","article-title":"Variational autoencoders and nonlinear ICA: A unifying framework","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Khemakhem","year":"2020"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01108"},{"key":"ref147","article-title":"I don\u2019t need u: Identifiable non-linear ICA without side information","author":"Willetts","year":"2021"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/273"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1141"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0027"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86520-7_40"},{"key":"ref152","first-page":"2376","article-title":"Counterfactual visual explanations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Goyal","year":"2019"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3507008"},{"key":"ref154","article-title":"Causal adversarial network for learning conditional and interventional distributions","author":"Moraffah","year":"2020"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1145\/3527154"},{"issue":"1","key":"ref156","first-page":"111","article-title":"Pairwise likelihood ratios for estimation of non-Gaussian structural equation models","volume":"14","author":"Hyv\u00e4rinen","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref157","article-title":"DAGS with no tears: Continuous optimization for structure learning","volume":"31","author":"Zheng","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref158","first-page":"18741","article-title":"Score matching enables causal discovery of nonlinear additive noise models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rolland","year":"2022"},{"key":"ref159","first-page":"3020","article-title":"Learning representations for counterfactual inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Johansson","year":"2016"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2552"},{"key":"ref161","first-page":"12768","article-title":"ICE-BEEM: Identifiable conditional energy-based deep models based on nonlinear ICA","volume":"33","author":"Khemakhem","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref163","article-title":"Infodiffusion: Representation learning using information maximizing diffusion models","author":"Wang","year":"2023"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1607"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02181"},{"key":"ref166","article-title":"Causal component analysis","author":"Liang","year":"2023"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2110"},{"key":"ref168","article-title":"Challenges and applications of large language models","author":"Kaddour","year":"2023"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977172.50"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7254-8_69"},{"key":"ref171","first-page":"1157","article-title":"Causal mosaic: Cause-effect inference via nonlinear ICA and ensemble method","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Wu","year":"2020"},{"key":"ref172","article-title":"Discovery and visualization of nonstationary causal models","author":"Zhang","year":"2016"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/187"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.114"},{"key":"ref175","first-page":"14891","article-title":"Generalized independent noise condition for estimating latent variable causal graphs","volume":"33","author":"Xie","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/2700476"},{"key":"ref177","article-title":"Towards causalGPT: A multi-agent approach for faithful knowledge reasoning via promoting causal consistency in LLMS","author":"Tang","year":"2023"},{"key":"ref178","article-title":"Benchmarking and explaining large language model-based code generation: A causality-centric approach","author":"Ji","year":"2023"},{"key":"ref179","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref182","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3491209","article-title":"Trustworthy artificial intelligence: A review","volume":"55","author":"Kaur","year":"2022","journal-title":"ACM Comput. Surveys (CSUR)"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17478-w"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00338-7"},{"key":"ref185","article-title":"Counterfactual fairness","volume":"30","author":"Kusner","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/199"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00996"},{"key":"ref188","first-page":"858","article-title":"Diffusion models for counterfactual explanations","volume-title":"Proc. Asian Conference Comput. Vis.","author":"Jeanneret","year":"2022"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_9"},{"key":"ref190","article-title":"A fine-grained analysis on distribution shift","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wiles","year":"2021"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref192","article-title":"Measuring axiomatic soundness of counterfactual image models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Monteiro","year":"2023"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.65109\/uyyq1151"},{"issue":"89","key":"ref194","first-page":"1","article-title":"Causal discovery from heterogeneous\/nonstationary data","volume":"21","author":"Huang","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"ref195","first-page":"24370","article-title":"Identification of linear non-Gaussian latent hierarchical structure","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie","year":"2022"},{"key":"ref196","article-title":"Structural intervention distance (SID) for evaluating causal graphs","author":"Peters","year":"2013"},{"key":"ref197","article-title":"In search of lost domain generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gulrajani","year":"2021"},{"key":"ref198","article-title":"Bayesian modeling of human concept learning","volume":"11","author":"Tenenbaum","year":"1998","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11589479\/11311568.pdf?arnumber=11311568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:39:10Z","timestamp":1782934750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11311568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":199,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3646958","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}