{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:07:20Z","timestamp":1757614040052,"version":"3.44.0"},"reference-count":58,"publisher":"Association for Computing Machinery (ACM)","issue":"11","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:p>Understanding the causal relationships between treatments and outcomes is fundamental in various areas. Causal inference aims to estimate the effect of one variable on another, and critically relies on access to those variables as well as the key confounders. Unfortunately, data analysts often start with datasets lacking these columns, leading to incorrect estimations. Relational data repositories hold significant potential to augment such datasets with an admissible set of confounders necessary for causal analysis. While recent work has advocated for this potential, these approaches face notable limitations. They either assume the existence of a complete causal diagram over all datasets in the repository, which is impractical; rely on computationally infeasible techniques that do not scale to large data repositories with many features; or can only detect confounders in the absence of causal relations, and are thus ineffective when a causal effect exists.<\/jats:p>\n          <jats:p>We observe that the asymmetry between causes and effects used in causal discovery can be exploited to directly identify confounders for causal queries. In this paper, we establish a connection between the existence of confounders and the presence of unconfounded ancestors of the treatment variable in the underlying causal diagram\u2014without requiring access to the diagram. This makes it feasible to iteratively discover confounders until an admissible set is constructed. We propose Suna, a highly optimized, GPU-compatible system that implements a novel end-to-end algorithm for discovering confounders within large relational data repositories. Experiments on both real-world and synthetic datasets demonstrate that our system effectively discovers high-quality confounders. Furthermore, Suna employs algorithmic optimizations to accelerate confounder discovery without materializing joins. Our experiments show that Suna finds high-quality confounders while running &gt;100x faster than existing confounder discovery systems.<\/jats:p>","DOI":"10.14778\/3749646.3749684","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T17:55:06Z","timestamp":1757008506000},"page":"4158-4170","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Suna: Scalable Causal Confounder Discovery over Relational Data"],"prefix":"10.14778","volume":"18","author":[{"given":"Jiaxiang","family":"Liu","sequence":"first","affiliation":[{"name":"Columbia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Xia","sequence":"additional","affiliation":[{"name":"University of Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Alabi","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugene","family":"Wu","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,4]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"[n.d.]. 2007-2008-School-Progress-Reports-All-Schools. https:\/\/data.cityofnewyork.us\/Education\/2007-2008-School-Progress-Reports-All-Schools\/dj4e-3xrn."},{"key":"e_1_2_1_2_1","unstructured":"[n.d.]. 2012 SAT Results. https:\/\/data.cityofnewyork.us\/Education\/2012-SAT-Results\/f9bf-2cp4."},{"key":"e_1_2_1_3_1","unstructured":"[n.d.]. 2013 \u2013 2018 School ELA REsults. https:\/\/data.cityofnewyork.us\/Education\/2013-2018-School-ELA-REsults\/qkpp-pbi8."},{"key":"e_1_2_1_4_1","unstructured":"[n.d.]. 2014\u201315 To 2016\u201317 School- Level NYC Regents Report For All Variables. https:\/\/data.cityofnewyork.us\/Education\/2014-15-To-2016-17-School-Level-NYC-Regents-Report\/csps-2ne9\/."},{"key":"e_1_2_1_5_1","unstructured":"[n.d.]. 2018 \u2013 2019 Class Size Pupil to Teacher Ratio. https:\/\/data.cityofnewyork.us\/Education\/2018-2019-Class-Size-Pupil-to-Teacher-Ratio\/axb2-9jkb."},{"key":"e_1_2_1_6_1","unstructured":"[n.d.]. SUNA Technical Report. https:\/\/anonymous.4open.science\/r\/causal_search-3CD5\/Suna.pdf."},{"key":"e_1_2_1_7_1","unstructured":"2022. NYC Open Data. https:\/\/opendata.cityofnewyork.us\/."},{"key":"e_1_2_1_8_1","volume-title":"Privacy and Security in Distributed Data Markets. In Companion of the 2025 International Conference on Management of Data (SIGMOD\/PODS '25)","author":"Alabi Daniel","year":"2025","unstructured":"Daniel Alabi, Sainyam Galhotra, Shagufta Mehnaz, Zeyu Song, and Eugene Wu. 2025. Privacy and Security in Distributed Data Markets. In Companion of the 2025 International Conference on Management of Data (SIGMOD\/PODS '25)."},{"key":"e_1_2_1_9_1","volume-title":"International conference on machine learning. PMLR, 884\u2013895","author":"Bica Ioana","year":"2020","unstructured":"Ioana Bica, Ahmed Alaa, and Mihaela Van Der Schaar. 2020. Time series de-confounder: Estimating treatment effects over time in the presence of hidden confounders. In International conference on machine learning. PMLR, 884\u2013895."},{"key":"e_1_2_1_10_1","volume-title":"Tim Kraska, and David Karger.","author":"Chepurko Nadiia","year":"2020","unstructured":"Nadiia Chepurko, Ryan Marcus, Emanuel Zgraggen, Raul Castro Fernandez, Tim Kraska, and David Karger. 2020. ARDA: automatic relational data augmentation for machine learning. arXiv preprint arXiv:2003.09758 (2020)."},{"key":"e_1_2_1_11_1","volume-title":"On the measure of intelligence. arXiv preprint arXiv:1911.01547","author":"Chollet Fran\u00e7ois","year":"2019","unstructured":"Fran\u00e7ois Chollet. 2019. On the measure of intelligence. arXiv preprint arXiv:1911.01547 (2019)."},{"key":"e_1_2_1_12_1","volume-title":"Empirical properties of asset returns: stylized facts and statistical issues. Quantitative finance 1, 2","author":"Cont Rama","year":"2001","unstructured":"Rama Cont. 2001. Empirical properties of asset returns: stylized facts and statistical issues. Quantitative finance 1, 2 (2001), 223."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.2307\/1401511"},{"key":"e_1_2_1_14_1","volume-title":"METAM: Goal-Oriented Data Discovery. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE, 2780\u20132793","author":"Galhotra Sainyam","year":"2023","unstructured":"Sainyam Galhotra, Yue Gong, and Raul Castro Fernandez. 2023. METAM: Goal-Oriented Data Discovery. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE, 2780\u20132793."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654957"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1265530.1265535"},{"key":"e_1_2_1_17_1","volume-title":"Confounding and collapsibility in causal inference. Statistical science 14, 1","author":"Greenland Sander","year":"1999","unstructured":"Sander Greenland, Judea Pearl, and James M Robins. 1999. Confounding and collapsibility in causal inference. Statistical science 14, 1 (1999), 29\u201346."},{"key":"e_1_2_1_18_1","unstructured":"Tobias Hatt and Stefan Feuerriegel. 2024. Sequential deconfounding for causal inference with unobserved confounders. In Causal Learning and Reasoning. PMLR 934\u2013956."},{"key":"e_1_2_1_19_1","volume-title":"Nonlinear causal discovery with additive noise models. Advances in neural information processing systems 21","author":"Hoyer Patrik","year":"2008","unstructured":"Patrik Hoyer, Dominik Janzing, Joris M Mooij, Jonas Peters, and Bernhard Sch\u00f6lkopf. 2008. Nonlinear causal discovery with additive noise models. Advances in neural information processing systems 21 (2008)."},{"key":"e_1_2_1_20_1","volume-title":"Raul Castro Fernandez, and Eugene Wu","author":"Huang Zezhou","year":"2023","unstructured":"Zezhou Huang, Jiaxiang Liu, Daniel Alabi, Raul Castro Fernandez, and Eugene Wu. 2023. Saibot: A Differentially Private Data Search Platform. arXiv preprint arXiv:2307.00432 (2023)."},{"key":"e_1_2_1_21_1","volume-title":"The Fast and the Private: Task-based Dataset Search. arXiv preprint arXiv:2308.05637","author":"Huang Zezhou","year":"2023","unstructured":"Zezhou Huang, Jiaxiang Liu, Haonan Wang, and Eugene Wu. 2023. The Fast and the Private: Task-based Dataset Search. arXiv preprint arXiv:2308.05637 (2023)."},{"key":"e_1_2_1_22_1","volume-title":"Causal machine learning and business decision making. Available at SSRN 3867326","author":"H\u00fcnermund Paul","year":"2022","unstructured":"Paul H\u00fcnermund, Jermain Kaminski, and Carla Schmitt. 2022. Causal machine learning and business decision making. Available at SSRN 3867326 (2022)."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2567709.2502585"},{"key":"e_1_2_1_24_1","first-page":"3679","article-title":"Causal identification under Markov equivalence: calculus, algorithm, and completeness","volume":"35","author":"Jaber Amin","year":"2022","unstructured":"Amin Jaber, Adele Ribeiro, Jiji Zhang, and Elias Bareinboim. 2022. Causal identification under Markov equivalence: calculus, algorithm, and completeness. Advances in Neural Information Processing Systems 35 (2022), 3679\u20133690.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_25_1","unstructured":"Kaggle. 2024. Kaggle Datasets Repository. https:\/\/www.kaggle.com\/datasets Accessed: 2024-10-15."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574274"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555041.3589732"},{"key":"e_1_2_1_28_1","volume-title":"Estimating mutual information. Physical Review E\u2014Statistical, Nonlinear, and Soft Matter Physics 69, 6","author":"Kraskov Alexander","year":"2004","unstructured":"Alexander Kraskov, Harald St\u00f6gbauer, and Peter Grassberger. 2004. Estimating mutual information. Physical Review E\u2014Statistical, Nonlinear, and Soft Matter Physics 69, 6 (2004), 066138."},{"key":"e_1_2_1_29_1","volume-title":"Towards Robust Relational Causal Discovery. In Conference on Uncertainty in Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:197660683","author":"Lee Sanghack","year":"2019","unstructured":"Sanghack Lee and Vasant G Honavar. 2019. Towards Robust Relational Causal Discovery. In Conference on Uncertainty in Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:197660683"},{"key":"e_1_2_1_30_1","volume-title":"High school size: Which works best and for whom? Educational evaluation and policy analysis 19, 3","author":"Lee Valerie E","year":"1997","unstructured":"Valerie E Lee and Julia B Smith. 1997. High school size: Which works best and for whom? Educational evaluation and policy analysis 19, 3 (1997), 205\u2013227."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3665601.3669847"},{"key":"e_1_2_1_32_1","unstructured":"Mark Maier. 2014. Causal Discovery for Relational Domains: Representation Reasoning and Learning. https:\/\/api.semanticscholar.org\/CorpusID:11057134"},{"key":"e_1_2_1_33_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Maier Marc E.","year":"2010","unstructured":"Marc E. Maier, Brian J. Taylor, H\u00fcseyin Oktay, and David D. Jensen. 2010. Learning Causal Models of Relational Domains. Proceedings of the AAAI Conference on Artificial Intelligence (2010). https:\/\/api.semanticscholar.org\/CorpusID:12408451"},{"key":"e_1_2_1_34_1","volume-title":"Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research), Sanjoy Dasgupta, Stephan Mandt, and Yingzhen Li (Eds.)","volume":"238","author":"Mameche Sarah","year":"2024","unstructured":"Sarah Mameche, Jilles Vreeken, and David Kaltenpoth. 2024. Identifying Confounding from Causal Mechanism Shifts. In Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research), Sanjoy Dasgupta, Stephan Mandt, and Yingzhen Li (Eds.), Vol. 238. PMLR, 4897\u20134905."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1257\/app.5.1.65"},{"key":"e_1_2_1_36_1","unstructured":"Judea Pearl. 2009. Causality. Cambridge university press."},{"key":"e_1_2_1_37_1","volume-title":"An introduction to causal inference. The international journal of biostatistics 6, 2","author":"Pearl Judea","year":"2010","unstructured":"Judea Pearl. 2010. An introduction to causal inference. The international journal of biostatistics 6, 2 (2010)."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1086\/700678"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196914"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389759"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00264"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/66.3.605"},{"key":"e_1_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Rajen D Shah and Jonas Peters. 2020. The hardness of conditional independence testing and the generalised covariance measure. (2020).","DOI":"10.1214\/19-AOS1857"},{"key":"e_1_2_1_44_1","article-title":"A linear non-Gaussian acyclic model for causal discovery","volume":"7","author":"Shimizu Shohei","year":"2006","unstructured":"Shohei Shimizu, Patrik O Hoyer, Aapo Hyv\u00e4rinen, Antti Kerminen, and Michael Jordan. 2006. A linear non-Gaussian acyclic model for causal discovery. Journal of Machine Learning Research 7, 10 (2006).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_1_45_1","first-page":"1225","article-title":"DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model","author":"Shimizu Shohei","year":"2011","unstructured":"Shohei Shimizu, Takanori Inazumi, Yasuhiro Sogawa, Aapo Hyvarinen, Yoshinobu Kawahara, Takashi Washio, Patrik O Hoyer, Kenneth Bollen, and Patrik Hoyer. 2011. DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model. Journal of Machine Learning Research-JMLR 12, Apr (2011), 1225\u20131248.","journal-title":"Journal of Machine Learning Research-JMLR 12"},{"key":"e_1_2_1_46_1","volume-title":"International Workshop on Artificial Intelligence and Statistics. PMLR, 278\u2013285","author":"Spirtes Peter","year":"2001","unstructured":"Peter Spirtes. 2001. An anytime algorithm for causal inference. In International Workshop on Artificial Intelligence and Statistics. PMLR, 278\u2013285."},{"volume-title":"prediction, and search","author":"Spirtes Peter","key":"e_1_2_1_47_1","unstructured":"Peter Spirtes, Clark Glymour, and Richard Scheines. 2001. Causation, prediction, and search. MIT press."},{"key":"e_1_2_1_48_1","unstructured":"Stack Overflow. 2024. Stack Overflow Developer Survey. https:\/\/insights.stackoverflow.com\/survey\/ Accessed: 2024-10-11."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-0285-1"},{"key":"e_1_2_1_50_1","unstructured":"Jin Tian and Judea Pearl. 2002. A general identification condition for causal effects. In Aaai\/iaai. 567\u2013573."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1982.10482778"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2019.1686987"},{"key":"e_1_2_1_53_1","first-page":"1","article-title":"Causal discovery with unobserved confounding and non-Gaussian data","volume":"24","author":"Samuel Wang Y","year":"2023","unstructured":"Y Samuel Wang and Mathias Drton. 2023. Causal discovery with unobserved confounding and non-Gaussian data. Journal of Machine Learning Research 24, 271 (2023), 1\u201361.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.32614\/CRAN.package.cbl"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639328"},{"key":"e_1_2_1_56_1","volume-title":"On Explaining Confounding Bias. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE","author":"Youngmann Brit","year":"2023","unstructured":"Brit Youngmann, Michael Cafarella, Yuval Moskovitch, and Babak Salimi. 2023. On Explaining Confounding Bias. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE, 1846\u20131859."},{"key":"e_1_2_1_57_1","volume-title":"Causal Data Integration. arXiv preprint arXiv:2305.08741","author":"Youngmann Brit","year":"2023","unstructured":"Brit Youngmann, Michael Cafarella, Babak Salimi, and Anna Zeng. 2023. Causal Data Integration. arXiv preprint arXiv:2305.08741 (2023)."},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300065"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3749646.3749684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T03:28:03Z","timestamp":1757042883000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3749646.3749684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":58,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.14778\/3749646.3749684"],"URL":"https:\/\/doi.org\/10.14778\/3749646.3749684","relation":{},"ISSN":["2150-8097"],"issn-type":[{"type":"print","value":"2150-8097"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"2025-09-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}