{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T18:45:07Z","timestamp":1747248307016,"version":"3.37.3"},"reference-count":56,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"ERC Synergy Grant USMILE","award":["855187"],"award-info":[{"award-number":["855187"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Causal discovery from observational data offers unique opportunities in many scientific disciplines: reconstructing causal drivers, testing causal hypotheses, and comparing and evaluating models for optimizing targeted interventions. Recent causal discovery methods focused on estimating the latent space of the data to get around a lack of causal sufficiency or additivity constraints. However, estimating the latent space significantly increases model complexity, compromising causal identifiability and making it hard to compare models that correspond to different causal hypotheses. We propose a kernel, non-parametric latent-space modelling approach and deal with the difficulty of comparing causal directions by measuring and controlling for the level of causal assumption fulfilment. We introduce a latent noise causal inference framework to estimate latent factors associated with the hypothesized causal direction by optimizing a loss function with kernel independence criteria. We extend the framework to work with time series using an additional time-dependent kernel regularizer. We discuss the additivity assumption and model complexity and give empirical evidence of performance in a wide range of synthetic and real causal discovery problems.<\/jats:p>","DOI":"10.1088\/2632-2153\/ace151","type":"journal-article","created":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T17:45:48Z","timestamp":1687628748000},"page":"035004","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning latent functions for causal discovery"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8410-6635","authenticated-orcid":true,"given":"Emiliano","family":"D\u00edaz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gherardo","family":"Varando","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J Emmanuel","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gustau","family":"Camps-Valls","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2023,7,12]]},"reference":[{"key":"mlstace151bib1","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1016\/j.tins.2022.06.003","article-title":"A call for more clarity around causality in neuroscience","volume":"45","author":"Barack","year":"2022","journal-title":"Trends Neurosci."},{"key":"mlstace151bib2","first-page":"pp 900","article-title":"Cause-effect inference by comparing regression errors","author":"Bloebaum","year":"2018","edition":"ed"},{"year":"2019","author":"Bueso","article-title":"Cross-information kernel causality test cross-information kernel causality: revisiting global teleconnections of ENSO over soil moisture and vegetation","key":"mlstace151bib3"},{"key":"mlstace151bib4","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1214\/14-AOS1260","article-title":"CAM: causal additive models, high-dimensional order search and penalized regression","volume":"42","author":"B\u00fchlmann","year":"2014","journal-title":"Ann. Stat."},{"key":"mlstace151bib5","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1162\/NECO_a_00599","article-title":"Causal discovery via reproducing kernel Hilbert space embeddings","volume":"26","author":"Chen","year":"2014","journal-title":"Neural Comput."},{"key":"mlstace151bib6","first-page":"pp 143","article-title":"Inferring deterministic causal relations","author":"Daniu\u0161is","year":"2010"},{"key":"mlstace151bib7","doi-asserted-by":"publisher","first-page":"1610","DOI":"10.1038\/s41598-022-05377-7","article-title":"Inferring causal relations from observational long-term carbon and water fluxes records","volume":"12","author":"Diaz","year":"2022","journal-title":"Sienti. Rep."},{"key":"mlstace151bib8","doi-asserted-by":"publisher","first-page":"1610","DOI":"10.1038\/s41598-022-05377-7","article-title":"Inferring causal relations from observational long-term carbon and water fluxes records","volume":"12","author":"D\u00edaz","year":"2022","journal-title":"Sci. Rep."},{"key":"mlstace151bib9","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1002\/9783527609970.ch17","article-title":"Granger causality: basic theory and application to neuroscience","author":"Ding","year":"2006"},{"key":"mlstace151bib10","first-page":"pp 489","article-title":"Kernel measures of conditional dependence","volume":"vol 20","author":"Fukumizu","year":"2008"},{"key":"mlstace151bib11","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2019.00524","article-title":"Review of causal discovery methods based on graphical models","volume":"10","author":"Glymour","year":"2019","journal-title":"Front. Genet."},{"key":"mlstace151bib12","article-title":"A kernel method for the two-sample-problem","volume":"vol 19","author":"Gretton","year":"2006"},{"key":"mlstace151bib13","first-page":"pp 63","article-title":"Measuring statistical dependence with Hilbert-Schmidt norms","author":"Gretton","year":"2005b"},{"key":"mlstace151bib14","first-page":"2075","article-title":"Kernel methods for measuring independence","volume":"6","author":"Gretton","year":"2005a","journal-title":"J. Mach. Learn. Res."},{"key":"mlstace151bib15","first-page":"pp 1205","article-title":"Optimal kernel choice for large-scale two-sample tests","volume":"vol 25","author":"Gretton","year":"2012"},{"key":"mlstace151bib16","first-page":"1","article-title":"Non-linear causal inference using Gaussianity measures","volume":"17","author":"Hern\u00e1ndez-Lobato","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"mlstace151bib17","first-page":"pp 689","article-title":"Nonlinear causal discovery with additive noise models","volume":"vol 21,","author":"Hoyer","year":"2009"},{"key":"mlstace151bib18","first-page":"pp 689","article-title":"Nonlinear causal discovery with additive noise models","author":"Hoyer","year":"2008"},{"year":"2019","author":"H\u00fcnermund","article-title":"Causal inference and data fusion in econometrics","key":"mlstace151bib19"},{"key":"mlstace151bib20","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/S0893-6080(98)00140-3","article-title":"Nonlinear independent component analysis: existence and uniqueness results","volume":"12","author":"Hyv\u00e4rinen","year":"1999","journal-title":"Neural Netw."},{"year":"2022","author":"Immer","article-title":"On the identifiability and estimation of causal location-scale noise models","key":"mlstace151bib21"},{"key":"mlstace151bib22","doi-asserted-by":"publisher","first-page":"5168","DOI":"10.1109\/TIT.2010.2060095","article-title":"Causal inference using the algorithmic Markov condition","volume":"56","author":"Janzing","year":"2010","journal-title":"IEEE Trans. Inf. Theory"},{"key":"mlstace151bib23","first-page":"2009","article-title":"Causal discovery with continuous additive noise models","volume":"15","author":"Jonas Peters","year":"2014","journal-title":"J. Mach. Learn. Res."},{"year":"2020","author":"Khemakhem","article-title":"Causal autoregressive flows","key":"mlstace151bib24"},{"year":"2006","author":"Lemeire","article-title":"Causal models as minimal descriptions of multivariate systems","key":"mlstace151bib25"},{"year":"2008","author":"Li","edition":"3rd edn","key":"mlstace151bib26"},{"key":"mlstace151bib27","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1109\/TPAMI.2018.2832198","article-title":"Aggregating randomized clustering-promoting invariant projections for domain adaptation","volume":"41","author":"Liang","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstace151bib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106996","article-title":"Exploring uncertainty in pseudo-label guided unsupervised domain adaptation","volume":"96","author":"Liang","year":"2019","journal-title":"Pattern Recognit."},{"key":"mlstace151bib29","first-page":"pp 1452","article-title":"Towards a learning theory of cause-effect inference","volume":"vol 37","author":"Lopez-Paz","year":"2015"},{"key":"mlstace151bib30","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1007\/s10115-018-1286-7","article-title":"Telling cause from effect by local and global regression","volume":"60","author":"Marx","year":"2019a","journal-title":"Knowl. Inf. Syst."},{"key":"mlstace151bib31","first-page":"pp 852","article-title":"Identifiability of cause and effect using regularized regression","author":"Marx","year":"2019b"},{"year":"2018","author":"Mitrovic","article-title":"Causal inference via kernel deviance measures","key":"mlstace151bib32"},{"year":"2020","author":"Monti","article-title":"Autoregressive flow-based causal discovery and inference","key":"mlstace151bib33"},{"key":"mlstace151bib34","first-page":"1","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":"mlstace151bib35","first-page":"pp 745","article-title":"Regression by dependence minimization and its application to causal inference in additive noise models","author":"Mooij","year":"2009"},{"year":"2009","author":"Pearl","edition":"2nd edn","key":"mlstace151bib36"},{"key":"mlstace151bib37","doi-asserted-by":"publisher","first-page":"1502","DOI":"10.1109\/TGRS.2018.2867002","article-title":"Causal inference in geoscience and remote sensing from observational data","volume":"57","author":"P\u00e9rez-Suay","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"year":"2017a","author":"Peters","key":"mlstace151bib38"},{"year":"2017b","author":"Peters","key":"mlstace151bib39"},{"volume":"vol 65","year":"1991","author":"Reichenbach","key":"mlstace151bib40"},{"year":"2018","author":"Rojo-\u00c1lvarez","key":"mlstace151bib41"},{"key":"mlstace151bib42","doi-asserted-by":"publisher","first-page":"S144","DOI":"10.2105\/AJPH.2004.059204","article-title":"Causation and causal inference in epidemiology","volume":"95","author":"Rothman","year":"2005","journal-title":"Am. J. Public Health"},{"key":"mlstace151bib43","doi-asserted-by":"publisher","first-page":"2553","DOI":"10.1038\/s41467-019-10105-3","article-title":"Inferring causation from time series with perspectives in Earth system sciences","volume":"10","author":"Runge","year":"2019a","journal-title":"Nat. Commun."},{"key":"mlstace151bib44","doi-asserted-by":"publisher","first-page":"eaau4996","DOI":"10.1126\/sciadv.aau4996","article-title":"Detecting and quantifying causal associations in large nonlinear time series datasets","volume":"5","author":"Runge","year":"2019b","journal-title":"Sci. Adv."},{"year":"2019","author":"Rustamov","article-title":"Closed-form expressions for maximum mean discrepancy with applications to Wasserstein auto-encoders","key":"mlstace151bib45"},{"year":"2002","author":"Sch\u00f6lkopf","key":"mlstace151bib46"},{"year":"2004","author":"Shawe-Taylor","key":"mlstace151bib47"},{"key":"mlstace151bib48","first-page":"2003","article-title":"A linear non-Gaussian acyclic model for causal discovery","volume":"7","author":"Shohei Shimizu","year":"2006","journal-title":"J. Mach. Learn. Res."},{"year":"2000","author":"Spirtes","edition":"2nd edn","key":"mlstace151bib49"},{"key":"mlstace151bib50","article-title":"Probabilistic latent variable models for distinguishing between cause and effect","volume":"vol 23","author":"Stegle","year":"2010"},{"key":"mlstace151bib51","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1126\/science.1227079","article-title":"Detecting causality in complex ecosystems","volume":"338","author":"Sugihara","year":"2012a","journal-title":"Science"},{"key":"mlstace151bib52","first-page":"pp 9311","article-title":"Distinguishing cause from effect using quantiles: bivariate quantile causal discovery","author":"Tagasovska","year":"2020"},{"year":"2020","author":"Ton","article-title":"Meta learning for causal direction","key":"mlstace151bib53"},{"key":"mlstace151bib54","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2018.03.005","article-title":"Adaptive batch normalization for practical domain adaptation","volume":"80","author":"Yanghao","year":"2018","journal-title":"Pattern Recognit."},{"key":"mlstace151bib55","first-page":"pp 647","article-title":"On the identifiability of the post-nonlinear causal model","author":"Zhang","year":"2009"},{"key":"mlstace151bib56","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1093\/nsr\/nwx137","article-title":"Learning causality and causality-related learning: some recent progress","volume":"5","author":"Zhang","year":"2018","journal-title":"Natl Sci. Rev."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T14:04:34Z","timestamp":1699538674000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,12]]},"references-count":56,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,7,12]]},"published-print":{"date-parts":[[2023,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ace151","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2023,7,12]]},"assertion":[{"value":"Learning latent functions for causal discovery","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-10-06","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-06-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-07-12","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}