{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:14:14Z","timestamp":1775088854406,"version":"3.50.1"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T00:00:00Z","timestamp":1675728000000},"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":["2020AAA0106000"],"award-info":[{"award-number":["2020AAA0106000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U19A2079, 62121002"],"award-info":[{"award-number":["U19A2079, 62121002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2023,7,31]]},"abstract":"<jats:p>\n            In recommender systems, some features directly affect whether an interaction would happen, making the happened interactions not necessarily indicate user preference. For instance, short videos are objectively easier to finish even though the user may not like the video. We term such feature as\n            <jats:italic>confounding feature<\/jats:italic>\n            , and video length is a confounding feature in video recommendation. If we fit a model on such interaction data, just as done by most data-driven recommender systems, the model will be biased to recommend short videos more, and deviate from user actual requirement.\n          <\/jats:p>\n          <jats:p>\n            This work formulates and addresses the problem from the causal perspective. Assuming there are some factors affecting both the confounding feature and other item features, e.g., the video creator, we find the confounding feature opens a backdoor path behind user-item matching and introduces spurious correlation. To remove the effect of backdoor path, we propose a framework named\n            <jats:italic>Deconfounding Causal Recommendation<\/jats:italic>\n            <jats:bold>(DCR)<\/jats:bold>\n            , which performs intervened inference with\n            <jats:italic>do-calculus<\/jats:italic>\n            . Nevertheless, evaluating\n            <jats:italic>do-calculus<\/jats:italic>\n            requires to sum over the prediction on all possible values of confounding feature, significantly increasing the time cost. To address the efficiency challenge, we further propose a\n            <jats:bold>mixture-of-experts (MoE)<\/jats:bold>\n            model architecture, modeling each value of confounding feature with a separate expert module. Through this way, we retain the model expressiveness with few additional costs. We demonstrate DCR on the backbone model of\n            <jats:bold>neural factorization machine (NFM)<\/jats:bold>\n            , showing that DCR leads to more accurate prediction of user preference with small inference time cost. We release our code at:\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"url\" xlink:href=\"https:\/\/github.com\/zyang1580\/DCR\">https:\/\/github.com\/zyang1580\/DCR<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3559757","type":"journal-article","created":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T12:14:54Z","timestamp":1661861694000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":48,"title":["Addressing Confounding Feature Issue for Causal Recommendation"],"prefix":"10.1145","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-7992","authenticated-orcid":false,"given":"Xiangnan","family":"He","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7863-5183","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-9842","authenticated-orcid":false,"given":"Fuli","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8109-4499","authenticated-orcid":false,"given":"Chonggang","family":"Song","sequence":"additional","affiliation":[{"name":"WeChat, Tencent, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8809-7676","authenticated-orcid":false,"given":"Lingling","family":"Yi","sequence":"additional","affiliation":[{"name":"WeChat, Tencent, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9398-3859","authenticated-orcid":false,"given":"Guohui","family":"Ling","sequence":"additional","affiliation":[{"name":"WeChat, Tencent, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}]}],"member":"320","published-online":{"date-parts":[[2023,2,7]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109912"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330745"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462919"},{"key":"e_1_3_2_5_2","article-title":"Bias and debias in recommender system: A survey and future directions","author":"Chen Jiawei","year":"2020","unstructured":"Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, and Xiangnan He. 2020. Bias and debias in recommender system: A survey and future directions. arXiv preprint arXiv:2010.03240 (2020).","journal-title":"arXiv preprint arXiv:2010.03240"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271742"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1145\/3383313.3412208","volume-title":"Fourteenth ACM Conference on Recommender Systems","author":"Christakopoulou Konstantina","year":"2020","unstructured":"Konstantina Christakopoulou, Madeleine Traverse, Trevor Potter, Emma Marriott, Daniel Li, Chris Haulk, Ed H. Chi, and Minmin Chen. 2020. Deconfounding user satisfaction estimation from response rate bias. In Fourteenth ACM Conference on Recommender Systems. ACM, 450\u2013455."},{"issue":"7","key":"e_1_3_2_8_2","article-title":"Adaptive subgradient methods for online learning and stochastic optimization.","volume":"12","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research 12, 7 (2011).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.0006-341X.2002.00021.x"},{"key":"e_1_3_2_10_2","first-page":"1725","volume-title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","author":"Guo Huifeng","year":"2017","unstructured":"Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. 2017. DeepFM: A factorization-machine based neural network for CTR prediction. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. 1725\u20131731."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403336"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080777"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/3488560.3498375","volume-title":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","author":"Huang Jin","year":"2022","unstructured":"Jin Huang, Harrie Oosterhuis, and Maarten de Rijke. 2022. It is different when items are older: Debiasing recommendations when selection bias and user preferences are dynamic. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. ACM, 381\u2013389."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449904"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186949"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511958"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449866"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462966"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401083"},{"key":"e_1_3_2_21_2","first-page":"351","volume-title":"Fifteenth ACM Conference on Recommender Systems","author":"Liu Dugang","year":"2021","unstructured":"Dugang Liu, Pengxiang Cheng, Hong Zhu, Zhenhua Dong, Xiuqiang He, Weike Pan, and Zhong Ming. 2021. Mitigating confounding bias in recommendation via information bottleneck. In Fifteenth ACM Conference on Recommender Systems. ACM, 351\u2013360."},{"key":"e_1_3_2_22_2","first-page":"4114","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Locatello Francesco","year":"2019","unstructured":"Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Raetsch, Sylvain Gelly, Bernhard Sch\u00f6lkopf, and Olivier Bachem. 2019. Challenging common assumptions in the unsupervised learning of disentangled representations. In Proceedings of the 36th International Conference on Machine Learning. PMLR, 4114\u20134124."},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1145\/3383313.3418491","volume-title":"Fourteenth ACM Conference on Recommender Systems","author":"Mehrotra Rishabh","year":"2020","unstructured":"Rishabh Mehrotra, Prasanta Bhattacharya, and Mounia Lalmas. 2020. Inferring the causal impact of new track releases on music recommendation platforms through counterfactual predictions. In Fourteenth ACM Conference on Recommender Systems. ACM, 687\u2013691."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0889-8588(05)70309-9"},{"key":"e_1_3_2_25_2","first-page":"561","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I. Jordan, and Ion Stoica. 2018. Ray: A distributed framework for emerging AI applications. In 13th USENIX Symposium on Operating Systems Design and Implementation. USENIX Association, 561\u2013577."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/1642718"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01087"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371783"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1145\/3383313.3412261","volume-title":"Fourteenth ACM Conference on Recommender Systems","author":"Sato Masahiro","year":"2020","unstructured":"Masahiro Sato, Sho Takemori, Janmajay Singh, and Tomoko Ohkuma. 2020. Unbiased learning for the causal effect of recommendation. In Fourteenth ACM Conference on Recommender Systems. ACM, 378\u2013387."},{"key":"e_1_3_2_31_2","first-page":"1670","volume-title":"Proceedings of the 33rd International Conference on Machine Learning","author":"Schnabel Tobias","year":"2016","unstructured":"Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as treatments: Debiasing learning and evaluation. In Proceedings of the 33rd International Conference on Machine Learning. PMLR, 1670\u20131679."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330933"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463005"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512010"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219869"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467249"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462962"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512251"},{"key":"e_1_3_2_39_2","article-title":"Causal disentanglement for semantics-aware intent learning in recommendation","author":"Wang Xiangmeng","year":"2022","unstructured":"Xiangmeng Wang, Qian Li, Dianer Yu, Peng Cui, Zhichao Wang, and Guandong Xu. 2022. Causal disentanglement for semantics-aware intent learning in recommendation. IEEE Transactions on Knowledge and Data Engineering (2022).","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441799"},{"issue":"528","key":"e_1_3_2_41_2","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1080\/01621459.2019.1686987","article-title":"The blessings of multiple causes","volume":"114","author":"Wang Yixin","year":"2019","unstructured":"Yixin Wang and David M. Blei. 2019. The blessings of multiple causes. J. Amer. Statist. Assoc. 114, 528 (2019), 1574\u20131596.","journal-title":"J. Amer. Statist. Assoc."},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1145\/3383313.3412225","volume-title":"Fourteenth ACM Conference on Recommender Systems","author":"Wang Yixin","year":"2020","unstructured":"Yixin Wang, Dawen Liang, Laurent Charlin, and David M. Blei. 2020. Causal inference for recommender systems. In Fourteenth ACM Conference on Recommender Systems. ACM, 426\u2013431."},{"key":"e_1_3_2_43_2","article-title":"A survey on the fairness of recommender systems","author":"Wang Yifan","year":"2022","unstructured":"Yifan Wang, Weizhi Ma, Min Zhang, Yiqun Liu, and Shaoping Ma. 2022. A survey on the fairness of recommender systems. ACM Trans. Inf. Syst. (2022). Just Accepted.","journal-title":"ACM Trans. Inf. Syst."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512092"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462855"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467289"},{"key":"e_1_3_2_47_2","first-page":"4462","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Wu Chuhan","year":"2021","unstructured":"Chuhan Wu, Fangzhao Wu, Xiting Wang, Yongfeng Huang, and Xing Xie. 2021. Fairness-aware news recommendation with decomposed adversarial learning. In Proceedings of the AAAI Conference on Artificial Intelligence. AAAI Press, 4462\u20134469."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450015"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498521"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000076"},{"key":"e_1_3_2_51_2","first-page":"2048","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In Proceedings of the 32nd International Conference on Machine Learning. JMLR, 2048\u20132057."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482305"},{"key":"e_1_3_2_53_2","first-page":"2921","volume-title":"the Thirty-first Conference on Neural Information Processing Systems","author":"Yao Sirui","year":"2017","unstructured":"Sirui Yao and Bert Huang. 2017. Beyond parity: Fairness objectives for collaborative filtering. In the Thirty-first Conference on Neural Information Processing Systems. 2921\u20132930."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.5555\/1795114.1795190"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462908"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462892"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462875"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449788"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467102"},{"key":"e_1_3_2_60_2","volume-title":"8th International Conference on Learning Representations","author":"Zhu Shengyu","year":"2020","unstructured":"Shengyu Zhu, Ignavier Ng, and Zhitang Chen. 2020. Causal discovery with reinforcement learning. In 8th International Conference on Learning Representations."},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441820"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271795"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3559757","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3559757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:07:57Z","timestamp":1750183677000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3559757"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,7]]},"references-count":61,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,7,31]]}},"alternative-id":["10.1145\/3559757"],"URL":"https:\/\/doi.org\/10.1145\/3559757","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,7]]},"assertion":[{"value":"2022-05-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-29","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}