{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T21:44:17Z","timestamp":1767908657462,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102420"],"award-info":[{"award-number":["62102420"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Public Computing Cloud, Renmin University of China"},{"name":"Intelligent Social Governance Platform, Major Innovation & Planning Interdisciplinary Platform for the Double First-Class Initiative, Renmin University of China"},{"name":"fund for building world-class universities (disciplines) of Renmin University of China"},{"name":"National Key R&D Program of China","award":["2023YFF0905402"],"award-info":[{"award-number":["2023YFF0905402"]}]},{"name":"Beijing Outstanding Young Scientist Program","award":["BJJWZYJH012019100020098"],"award-info":[{"award-number":["BJJWZYJH012019100020098"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671705","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"839-850","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Policy-Based Bayesian Active Causal Discovery with Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9743-2732","authenticated-orcid":false,"given":"Heyang","family":"Gao","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6727-6242","authenticated-orcid":false,"given":"Zexu","family":"Sun","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5365-897X","authenticated-orcid":false,"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0144-1775","authenticated-orcid":false,"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622420.1622432"},{"key":"e_1_3_2_2_2_1","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 3400--3409","author":"Agrawal Raj","year":"2019","unstructured":"Raj Agrawal, Chandler Squires, Karren Yang, Karthikeyan Shanmugam, and Caroline Uhler. 2019. Abcd-strategy: Budgeted experimental design for targeted causal structure discovery. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 3400--3409."},{"key":"e_1_3_2_2_3_1","volume-title":"Differentiable Multi-Target Causal Bayesian Experimental Design. arXiv preprint arXiv:2302.10607","author":"Annadani Yashas","year":"2023","unstructured":"Yashas Annadani, Panagiotis Tigas, Desi R Ivanova, Andrew Jesson, Yarin Gal, Adam Foster, and Stefan Bauer. 2023. Differentiable Multi-Target Causal Bayesian Experimental Design. arXiv preprint arXiv:2302.10607 (2023)."},{"key":"e_1_3_2_2_4_1","volume-title":"Emergence of scaling in random networks. science","author":"Barab\u00e1si Albert-L\u00e1szl\u00f3","year":"1999","unstructured":"Albert-L\u00e1szl\u00f3 Barab\u00e1si and R\u00e9ka Albert. 1999. Emergence of scaling in random networks. science, Vol. 286, 5439 (1999), 509--512."},{"key":"e_1_3_2_2_5_1","volume-title":"International Conference on Machine Learning. PMLR, 2107--2128","author":"Blau Tom","year":"2022","unstructured":"Tom Blau, Edwin V Bonilla, Iadine Chades, and Amir Dezfouli. 2022. Optimizing sequential experimental design with deep reinforcement learning. In International Conference on Machine Learning. PMLR, 2107--2128."},{"key":"e_1_3_2_2_6_1","volume-title":"Bayesian experimental design: A review. Statistical science","author":"Chaloner Kathryn","year":"1995","unstructured":"Kathryn Chaloner and Isabella Verdinelli. 1995. Bayesian experimental design: A review. Statistical science (1995), 273--304."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2006.00553.x"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2012.730083"},{"key":"e_1_3_2_2_9_1","volume-title":"On random graphs I. Publ. math. debrecen","author":"P","year":"1959","unstructured":"P ERDdS and A R&wi. 1959. On random graphs I. Publ. math. debrecen, Vol. 6, 290--297 (1959), 18."},{"key":"e_1_3_2_2_10_1","volume-title":"International Conference on Machine Learning. PMLR, 3384--3395","author":"Foster Adam","year":"2021","unstructured":"Adam Foster, Desi R Ivanova, Ilyas Malik, and Tom Rainforth. 2021. Deep adaptive design: Amortizing sequential bayesian experimental design. In International Conference on Machine Learning. PMLR, 3384--3395."},{"key":"e_1_3_2_2_11_1","volume-title":"Thomas Rainforth, and Noah Goodman.","author":"Foster Adam","year":"2019","unstructured":"Adam Foster, Martin Jankowiak, Elias Bingham, Paul Horsfall, Yee Whye Teh, Thomas Rainforth, and Noah Goodman. 2019. Variational Bayesian optimal experimental design. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_12_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 2959--2969","author":"Foster Adam","year":"2020","unstructured":"Adam Foster, Martin Jankowiak, Matthew O'Meara, Yee Whye Teh, and Tom Rainforth. 2020. A unified stochastic gradient approach to designing bayesian-optimal experiments. In International Conference on Artificial Intelligence and Statistics. PMLR, 2959--2969."},{"key":"e_1_3_2_2_13_1","volume-title":"Data analysis with Bayesian networks: A bootstrap approach. arXiv preprint arXiv:1301.6695","author":"Friedman Nir","year":"2013","unstructured":"Nir Friedman, Moises Goldszmidt, and Abraham Wyner. 2013. Data analysis with Bayesian networks: A bootstrap approach. arXiv preprint arXiv:1301.6695 (2013)."},{"key":"e_1_3_2_2_14_1","first-page":"15464","article-title":"Active invariant causal prediction: Experiment selection through stability","volume":"33","author":"Gamella Juan L","year":"2020","unstructured":"Juan L Gamella and Christina Heinze-Deml. 2020. Active invariant causal prediction: Experiment selection through stability. Advances in Neural Information Processing Systems, Vol. 33 (2020), 15464--15475.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_15_1","volume-title":"Enric Boix Adsera, and Guy Bresler","author":"Greenewald Kristjan","year":"2019","unstructured":"Kristjan Greenewald, Dmitriy Katz, Karthikeyan Shanmugam, Sara Magliacane, Murat Kocaoglu, Enric Boix Adsera, and Guy Bresler. 2019. Sample efficient active learning of causal trees. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0013397"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188410"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2503308.2503320"},{"key":"e_1_3_2_2_19_1","first-page":"2523","article-title":"Active learning of causal networks with intervention experiments and optimal designs","volume":"9","author":"He Yang-Bo","year":"2008","unstructured":"Yang-Bo He and Zhi Geng. 2008. Active learning of causal networks with intervention experiments and optimal designs. Journal of Machine Learning Research, Vol. 9, Nov (2008), 2523--2547.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_20_1","volume-title":"Bayesian active learning for classification and preference learning. arXiv preprint arXiv:1112.5745","author":"Houlsby Neil","year":"2011","unstructured":"Neil Houlsby, Ferenc Husz\u00e1r, Zoubin Ghahramani, and M\u00e1t\u00e9 Lengyel. 2011. Bayesian active learning for classification and preference learning. arXiv preprint arXiv:1112.5745 (2011)."},{"key":"e_1_3_2_2_21_1","volume-title":"Sequential Bayesian optimal experimental design via approximate dynamic programming. arXiv preprint arXiv:1604.08320","author":"Huan Xun","year":"2016","unstructured":"Xun Huan and Youssef M Marzouk. 2016. Sequential Bayesian optimal experimental design via approximate dynamic programming. arXiv preprint arXiv:1604.08320 (2016)."},{"key":"e_1_3_2_2_22_1","first-page":"25785","article-title":"Implicit deep adaptive design: policy-based experimental design without likelihoods","volume":"34","author":"Ivanova Desi R","year":"2021","unstructured":"Desi R Ivanova, Adam Foster, Steven Kleinegesse, Michael U Gutmann, and Thomas Rainforth. 2021. Implicit deep adaptive design: policy-based experimental design without likelihoods. Advances in Neural Information Processing Systems, Vol. 34 (2021), 25785--25798.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_23_1","volume-title":"International Conference on Machine Learning. PMLR, 4794--4803","author":"Jiang Shali","year":"2020","unstructured":"Shali Jiang, Henry Chai, Javier Gonzalez, and Roman Garnett. 2020. BINOCULARS for efficient, nonmyopic sequential experimental design. In International Conference on Machine Learning. PMLR, 4794--4803."},{"key":"e_1_3_2_2_24_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Kocaoglu Murat","year":"2017","unstructured":"Murat Kocaoglu, Alex Dimakis, and Sriram Vishwanath. 2017. Cost-optimal learning of causal graphs. In International Conference on Machine Learning. PMLR, 1875--1884."},{"key":"e_1_3_2_2_25_1","volume-title":"Sequential optimal design of neurophysiology experiments. Neural computation","author":"Lewi Jeremy","year":"2009","unstructured":"Jeremy Lewi, Robert Butera, and Liam Paninski. 2009. Sequential optimal design of neurophysiology experiments. Neural computation, Vol. 21, 3 (2009), 619--687."},{"key":"e_1_3_2_2_26_1","volume-title":"Policy-based bayesian experimental design for non-differentiable implicit models. arXiv preprint arXiv:2203.04272","author":"Lim Vincent","year":"2022","unstructured":"Vincent Lim, Ellen Novoseller, Jeffrey Ichnowski, Huang Huang, and Ken Goldberg. 2022. Policy-based bayesian experimental design for non-differentiable implicit models. arXiv preprint arXiv:2203.04272 (2022)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177728069"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2013.02.017"},{"key":"e_1_3_2_2_29_1","volume-title":"Methods matter: Improving causal inference in educational and social science research","author":"Murnane Richard J","unstructured":"Richard J Murnane and John B Willett. 2010. Methods matter: Improving causal inference in educational and social science research. Oxford University Press."},{"key":"e_1_3_2_2_31_1","volume-title":"Estimating drug effects in the presence of placebo response: causal inference using growth mixture modeling. Statistics in medicine","author":"Muth\u00e9n Bengt","year":"2009","unstructured":"Bengt Muth\u00e9n and Hendricks C Brown. 2009. Estimating drug effects in the presence of placebo response: causal inference using growth mixture modeling. Statistics in medicine, Vol. 28, 27 (2009), 3363--3385."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2013.05.005"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56970-3_9"},{"key":"e_1_3_2_2_34_1","volume-title":"From correlation to causation networks: a simple approximate learning algorithm and its application to high-dimensional plant gene expression data. BMC systems biology","author":"Opgen-Rhein Rainer","year":"2007","unstructured":"Rainer Opgen-Rhein and Korbinian Strimmer. 2007. From correlation to causation networks: a simple approximate learning algorithm and its application to high-dimensional plant gene expression data. BMC systems biology, Vol. 1, 1 (2007), 1--10."},{"key":"e_1_3_2_2_35_1","volume-title":"Causal inference. Causality: objectives and assessment","author":"Pearl Judea","year":"2010","unstructured":"Judea Pearl. 2010. Causal inference. Causality: objectives and assessment (2010), 39--58."},{"key":"e_1_3_2_2_36_1","volume-title":"Structural intervention distance for evaluating causal graphs. Neural computation","author":"Peters Jonas","year":"2015","unstructured":"Jonas Peters and Peter B\u00fchlmann. 2015. Structural intervention distance for evaluating causal graphs. Neural computation, Vol. 27, 3 (2015), 771--799."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12167"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.elerap.2019.100837"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/insr.12107"},{"key":"e_1_3_2_2_40_1","volume-title":"Science","volume":"308","author":"Sachs Karen","year":"2005","unstructured":"Karen Sachs, Omar Perez, Dana Pe'er, Douglas A Lauffenburger, and Garry P Nolan. 2005. Causal protein-signaling networks derived from multiparameter single-cell data. Science, Vol. 308, 5721 (2005), 523--529."},{"key":"e_1_3_2_2_41_1","volume-title":"Learning neural causal models with active interventions. arXiv preprint arXiv:2109.02429","author":"Scherrer Nino","year":"2021","unstructured":"Nino Scherrer, Olexa Bilaniuk, Yashas Annadani, Anirudh Goyal, Patrick Schwab, Bernhard Sch\u00f6lkopf, Michael C Mozer, Yoshua Bengio, Stefan Bauer, and Nan Rosemary Ke. 2021. Learning neural causal models with active interventions. arXiv preprint arXiv:2109.02429 (2021)."},{"key":"e_1_3_2_2_42_1","volume-title":"Advances in Neural Information Processing Systems","volume":"26","author":"Shababo Ben","year":"2013","unstructured":"Ben Shababo, Brooks Paige, Ari Pakman, and Liam Paninski. 2013. Bayesian inference and online experimental design for mapping neural microcircuits. Advances in Neural Information Processing Systems, Vol. 26 (2013)."},{"key":"e_1_3_2_2_43_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Shanmugam Karthikeyan","year":"2015","unstructured":"Karthikeyan Shanmugam, Murat Kocaoglu, Alexandros G Dimakis, and Sriram Vishwanath. 2015. Learning causal graphs with small interventions. Advances in Neural Information Processing Systems, Vol. 28 (2015)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2023.116304"},{"key":"e_1_3_2_2_45_1","first-page":"21500","article-title":"Active structure learning of causal DAGs via directed clique trees","volume":"33","author":"Squires Chandler","year":"2020","unstructured":"Chandler Squires, Sara Magliacane, Kristjan Greenewald, Dmitriy Katz, Murat Kocaoglu, and Karthikeyan Shanmugam. 2020. Active structure learning of causal DAGs via directed clique trees. Advances in Neural Information Processing Systems, Vol. 33 (2020), 21500--21511.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_46_1","first-page":"24130","article-title":"Interventions, where and how? experimental design for causal models at scale","volume":"35","author":"Tigas Panagiotis","year":"2022","unstructured":"Panagiotis Tigas, Yashas Annadani, Andrew Jesson, Bernhard Sch\u00f6lkopf, Yarin Gal, and Stefan Bauer. 2022. Interventions, where and how? experimental design for causal models at scale. Advances in Neural Information Processing Systems, Vol. 35 (2022), 24130--24143.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_47_1","volume-title":"International joint conference on artificial intelligence","author":"Tong Simon","unstructured":"Simon Tong and Daphne Koller. 2001. Active learning for structure in Bayesian networks. In International joint conference on artificial intelligence, Vol. 17. Citeseer, 863--869."},{"key":"e_1_3_2_2_48_1","first-page":"16261","article-title":"Active bayesian causal inference","volume":"35","author":"Toth Christian","year":"2022","unstructured":"Christian Toth, Lars Lorch, Christian Knoll, Andreas Krause, Franz Pernkopf, Robert Peharz, and Julius Von K\u00fcgelgen. 2022. Active bayesian causal inference. Advances in Neural Information Processing Systems, Vol. 35 (2022), 16261--16275.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_49_1","volume-title":"The max-min hill-climbing Bayesian network structure learning algorithm. Machine learning","author":"Tsamardinos Ioannis","year":"2006","unstructured":"Ioannis Tsamardinos, Laura E Brown, and Constantin F Aliferis. 2006. The max-min hill-climbing Bayesian network structure learning algorithm. Machine learning, Vol. 65 (2006), 31--78."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bts092"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Thomas S Verma and Judea Pearl. 2022. Equivalence and synthesis of causal models. In Probabilistic and causal inference: The works of Judea Pearl. 221--236.","DOI":"10.1145\/3501714.3501732"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.31234\/osf.io\/yehjb"},{"key":"e_1_3_2_2_53_1","first-page":"19923","article-title":"Matching a desired causal state via shift interventions","volume":"34","author":"Zhang Jiaqi","year":"2021","unstructured":"Jiaqi Zhang, Chandler Squires, and Caroline Uhler. 2021. Matching a desired causal state via shift interventions. Advances in Neural Information Processing Systems, Vol. 34 (2021), 19923--19934.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_54_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhang Zeyu","year":"2024","unstructured":"Zeyu Zhang, Chaozhuo Li, Xu Chen, and Xing Xie. 2024. Bayesian Active Causal Discovery with Multi-Fidelity Experiments. Advances in Neural Information Processing Systems, Vol. 36 (2024)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671705","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:00Z","timestamp":1750291560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":53,"alternative-id":["10.1145\/3637528.3671705","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671705","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}