{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T01:41:51Z","timestamp":1784598111114,"version":"3.55.0"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0101900"],"award-info":[{"award-number":["2018AAA0101900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61625107 and 62006207"],"award-info":[{"award-number":["61625107 and 62006207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key R & D Projects of the Ministry of Science and Technology","award":["2020YFC0832500"],"award-info":[{"award-number":["2020YFC0832500"]}]},{"name":"Fundamental Research Funds for the Central Universities and Zhejiang Province Natural Science Foundation","award":["LQ21F020020"],"award-info":[{"award-number":["LQ21F020020"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["72171131"],"award-info":[{"award-number":["72171131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Tsinghua University Initiative Scientific Research Grant","award":["2019THZWJC11"],"award-info":[{"award-number":["2019THZWJC11"]}]},{"name":"Technology and Innovation Major Project of the Ministry of Science and Technology of China","award":["2020AAA0108400 and 2020AAA01084020108403"],"award-info":[{"award-number":["2020AAA0108400 and 2020AAA01084020108403"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2022,8,31]]},"abstract":"<jats:p>Instrumental variables (IVs), sources of treatment randomization that are conditionally independent of the outcome, play an important role in causal inference with unobserved confounders. However, the existing IV-based counterfactual prediction methods need well-predefined IVs, while it\u2019s an art rather than science to find valid IVs in many real-world scenes. Moreover, the predefined hand-made IVs could be weak or erroneous by violating the conditions of valid IVs. These thorny facts hinder the application of the IV-based counterfactual prediction methods. In this article, we propose a novel Automatic Instrumental Variable decomposition (AutoIV) algorithm to automatically generate representations serving the role of IVs from observed variables (IV candidates). Specifically, we let the learned IV representations satisfy the relevance condition with the treatment and exclusion condition with the outcome via mutual information maximization and minimization constraints, respectively. We also learn confounder representations by encouraging them to be relevant to both the treatment and the outcome. The IV and confounder representations compete for the information with their constraints in an adversarial game, which allows us to get valid IV representations for IV-based counterfactual prediction. Extensive experiments demonstrate that our method generates valid IV representations for accurate IV-based counterfactual prediction.<\/jats:p>","DOI":"10.1145\/3494568","type":"journal-article","created":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T20:51:00Z","timestamp":1641675060000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0012-7397","authenticated-orcid":false,"given":"Junkun","family":"Yuan","sequence":"first","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anpeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Kuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runze","family":"Wu","sequence":"additional","affiliation":[{"name":"NetEase Fuxi AI Lab, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanfen","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,1,8]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441452"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4j72"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454607"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyv080"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/gepi.21965"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6835"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyt093"},{"key":"e_1_3_2_9_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Cheng Pengyu","year":"2020","unstructured":"Pengyu Cheng, Weituo Hao, Shuyang Dai, Jiachang Liu, Zhe Gan, and Carin Lawrence. 2020. CLUB: A contrastive log-ratio upper bound of mutual information. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.190671"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.3982\/ECTA6539"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6358"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2010.152"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2873325"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.2307\/1913851"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.econlet.2008.09.004"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.2307\/1912775"},{"key":"e_1_3_2_18_2","first-page":"4096","volume-title":"International Conference on Machine Learning","author":"Hartford Jason S.","year":"2021","unstructured":"Jason S. Hartford, Victor Veitch, Dhanya Sridhar, and Kevin Leyton-Brown. 2021. Valid causal inference with (some) invalid instruments. In International Conference on Machine Learning. PMLR, 4096\u20134106."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305527"},{"key":"e_1_3_2_20_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hassanpour Negar","year":"2020","unstructured":"Negar Hassanpour and Russell Greiner. 2020. Learning disentangled representations for counterfactual regression. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045708"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2014.994705"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2861006"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220082"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3365677"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098032"},{"key":"e_1_3_2_27_2","volume-title":"IEEE Transactions on Knowledge and Data Engineering","author":"Kuang Kun","year":"2020","unstructured":"Kun Kuang, Peng Cui, Hao Zou, Bo Li, Jianrong Tao, Fei Wu, and Shiqiang Yang. 2020. Data-Driven variable decomposition for treatment effect estimation. IEEE Transactions on Knowledge and Data Engineering (2020), online. DOI:10.1109\/TKDE.2020.3006898"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477052"},{"key":"e_1_3_2_29_2","first-page":"398","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Kuang Zhaobin","year":"2020","unstructured":"Zhaobin Kuang, Frederic Sala, Nimit Sohoni, Sen Wu, 6Aldo C\u00f3rdova-Palomera, Jared Dunnmon, James Priest, and Christopher R\u00e9. 2020. Ivy: Instrumental variable synthesis for causal inference. In International Conference on Artificial Intelligence and Statistics. PMLR, 398\u2013410."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_31_2","first-page":"12248","article-title":"Minimax estimation of conditional moment models.","volume":"33","author":"Dikkala Nishanth","year":"2020","unstructured":"Nishanth Dikkala, Greg Lewis, Lester Mackey, and Vasilis Syrgkanis. 2020. Minimax estimation of conditional moment models. In Advances in Neural Information Processing Systems, Vol. 33. 12248\u201312262.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_32_2","first-page":"2710","article-title":"Dual instrumental variable regression","volume":"33","author":"Muandet Krikamol","year":"2020","unstructured":"Krikamol Muandet, Arash Mehrjou, Si Kai Lee, and Anant Raj. 2020. Dual instrumental variable regression. In Advances in Neural Information Processing Systems, Vol. 33. 2710\u20132721.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00459"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"e_1_3_2_35_2","unstructured":"Aaron van den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv:1807.03748. Retrieved from https:\/\/arxiv.org\/abs\/1807.03748."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2946162"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305999"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454700"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2606428"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00308"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1498346"},{"key":"e_1_3_2_42_2","article-title":"Econometric analysis of cross section and panel data MIT press","volume":"108","author":"Wooldridge Jeffrey M.","year":"2002","unstructured":"Jeffrey M. Wooldridge. 2002. Econometric analysis of cross section and panel data MIT press. Cambridge, MA 108, 2 (2002), 245\u2013254.","journal-title":"Cambridge, MA"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rie.2016.01.001"},{"key":"e_1_3_2_44_2","volume-title":"Tariff on animal and vegetable oils","author":"Wright Philip G.","year":"1928","unstructured":"Philip G. Wright. 1928. Tariff on animal and vegetable oils. Macmillan Company, New York."},{"key":"e_1_3_2_45_2","unstructured":"Anpeng Wu Kun Kuang Junkun Yuan Bo Li Pan Zhou Jianrong Tao Qiang Zhu Yueting Zhuang and Fei Wu. 2020. Learning decomposed representation for counterfactual inference. arXiv:2006.07040. Retrieved from https:\/\/arxiv.org\/abs\/2006.07040."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3444944"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367471.3367612"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3436891"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00848"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3494568","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3494568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:16Z","timestamp":1750188676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3494568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,8]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8,31]]}},"alternative-id":["10.1145\/3494568"],"URL":"https:\/\/doi.org\/10.1145\/3494568","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,8]]},"assertion":[{"value":"2021-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}