{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T03:16:19Z","timestamp":1785381379722,"version":"3.55.0"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62472196"],"award-info":[{"award-number":["62472196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Jilin Science and Technology Research Project","award":["20230101067JC"],"award-info":[{"award-number":["20230101067JC"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176014"],"award-info":[{"award-number":["62176014"]}],"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":[[2025,11,30]]},"abstract":"<jats:p>\n            Inferring user preferences from users\u2019 historical feedback is a valuable problem in recommender systems. Conventional approaches often rely on the assumption that user preferences in the feedback data are equivalent to the real user preferences without additional noise, which simplifies the problem modeling. However, there are various confounders during user\u2013item interactions, such as weather and even the recommendation system itself. Therefore, neglecting the influence of confounders will result in inaccurate user preferences and suboptimal performance of the model. Furthermore, the unobservability of confounders poses a challenge in further addressing the problem. Along these lines, we refine the problem and propose a more rational solution to mitigate the influence of unobserved confounders. Specifically, we consider the influence of unobserved confounders, disentangle them from user preferences in the latent space, and employ causal graphs to model their interdependencies without specific labels. By ingeniously combining local and global causal graphs, we capture the user-specific effects of confounders on user preferences. Finally, we propose our model based on Variational Autoencoders, named\n            <jats:bold>Causal Structure Aware Variational Autoencoders (CSA-VAE)<\/jats:bold>\n            and theoretically demonstrate the identifiability of the obtained causal graph. We conducted extensive experiments on one synthetic dataset and nine real-world datasets with different scales, including three unbiased datasets and six normal datasets, where the average performance boost against several state-of-the-art baselines achieves up to 9.55%, demonstrating the superiority of our model. Furthermore, users can control their recommendation list by manipulating the learned causal representations of confounders, generating potentially more diverse recommendation results. Our code is available at Code-link (\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/MICLab-Rec\/CSA\">https:\/\/github.com\/MICLab-Rec\/CSA<\/jats:ext-link>\n            ).\n          <\/jats:p>","DOI":"10.1145\/3731447","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T09:51:54Z","timestamp":1745315514000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Causal Structure Representation Learning of Unobserved Confounders in Latent Space for Recommendation"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4597-5405","authenticated-orcid":false,"given":"Hangtong","family":"Xu","sequence":"first","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8370-5011","authenticated-orcid":false,"given":"Yuanbo","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8179-7503","authenticated-orcid":false,"given":"Chaozhuo","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9170-7009","authenticated-orcid":false,"given":"Fuzhen","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923)","author":"Chen Xu","year":"2024","unstructured":"Xu Chen, Jingsen Zhang, Lei Wang, Quanyu Dai, Zhenhua Dong, Ruiming Tang, Rui Zhang, Li Chen, Wayne Xin Zhao, and Ji-Rong Wen. 2024. REASONER: an explainable recommendation dataset with comprehensive labeling ground truths. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923). Curran Associates Inc., Red Hook, NY, USA, Article 638, 19 pages."},{"key":"e_1_3_2_3_2","unstructured":"MMEngine Contributors. 2022. MMEngine: OpenMMLab Foundational Library for Training Deep Learning Models. Retrieved from https:\/\/github.com\/open-mmlab\/mmengine"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40065-x"},{"key":"e_1_3_2_6_2","unstructured":"Yiheng Jiang Yuanbo Xu Yongjian Yang Funing Yang Pengyang Wang and Hui Xiong. 2023. TriMLP: Revenge of a MLP-like architecture in sequential recommendation. arXiv:2305.14675. Retrieved from https:\/\/arxiv.org\/abs\/2305.14675"},{"key":"e_1_3_2_7_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2013","unstructured":"Diederik P. Kingma and Max Welling. 2013. Auto-encoding variational bayes. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_8_2","unstructured":"Murat Kocaoglu Christopher Snyder Alexandros G. Dimakis and Sriram Vishwanath. 2017. CausalGAN: Learning causal implicit generative models with adversarial training. arXiv:1709.02023. Retrieved from https:\/\/arxiv.org\/abs\/1709.02023"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_10_2","unstructured":"S\u00e9bastien Lachapelle Philippe Brouillard Tristan Deleu and Simon Lacoste-Julien. 2019. Gradient-based neural DAG learning. arXiv:1906.02226. Retrieved from https:\/\/arxiv.org\/abs\/1906.02226"},{"key":"e_1_3_2_11_2","unstructured":"Dawen Liang Rahul G. Krishnan Matthew D. Hoffman and Tony Jebara. 2018. Variational autoencoders for collaborative filtering. arXiv:1802.05814. Retrieved from https:\/\/arxiv.org\/abs\/1802.05814"},{"key":"e_1_3_2_12_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. Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.), PMLR, 4114\u20134124. Retrieved from https:\/\/proceedings.mlr.press\/v97\/locatello19a.html"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2024.100590"},{"key":"e_1_3_2_14_2","article-title":"Learning disentangled representations for recommendation","volume":"32","author":"Ma Jianxin","year":"2019","unstructured":"Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, and Wenwu Zhu. 2019. Learning disentangled representations for recommendation. In Proceedings of the Advances in Neural Information Processing Systems. Vol. 32.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_15_2","unstructured":"Christopher Maddison Andriy Mnih and Yee Teh. 2017. The Concrete distribution: A continuous relaxation of discrete random variables. arXiv:1611.00712. Retrieved from https:\/\/arxiv.org\/abs\/1611.00712"},{"key":"e_1_3_2_16_2","unstructured":"Ignavier Ng Shengyu Zhu Zhuangyan Fang Haoyang Li Zhitang Chen and Jun Wang. 2022. Masked Gradient-Based causal structure learning. arXiv:1910.08527. Retrieved from https:\/\/arxiv.org\/abs\/1910.08527"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Judea Pearl. 2009. Causal inference in statistics: An overview. Statistic Surveys 3 (2009) 96\u2013146. DOI: 10.1214\/09-SS057","DOI":"10.1214\/09-SS057"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670315"},{"key":"e_1_3_2_19_2","first-page":"1","article-title":"Weakly supervised disentangled generative causal representation learning","volume":"23","author":"Shen Xinwei","year":"2022","unstructured":"Xinwei Shen, Furui Liu, Hanze Dong, Qing Lian, Zhitang Chen, and Tong Zhang. 2022. Weakly supervised disentangled generative causal representation learning. Journal of Machine Learning Research 23 (2022), 1\u201355. Retrieved from http:\/\/jmlr.org\/papers\/v23\/21-0080.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371831"},{"key":"e_1_3_2_21_2","first-page":"3","volume-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics","author":"Tillman Robert","year":"2011","unstructured":"Robert Tillman and Peter Spirtes. 2011. Learning equivalence classes of acyclic models with latent and selection variables from multiple datasets with overlapping variables. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. Geoffrey Gordon, David Dunson, and Miroslav Dud\u00edk (Eds.), PMLR, 3\u201315. Retrieved from https:\/\/proceedings.mlr.press\/v15\/tillman11a.html"},{"key":"e_1_3_2_22_2","first-page":"11","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten Laurens","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9 (2008), 11.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00202"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591961"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467249"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3153112"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539439"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835837"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5555-4_5"},{"key":"e_1_3_2_30_2","unstructured":"Hangtong Xu Yuanbo Xu Yongjian Yang Fuzhen Zhuang and Hui Xiong. 2023. DPR: An algorithm mitigate bias accumulation in recommendation feedback loops. arXiv:2311.05864. Retrieved from https:\/\/arxiv.org\/abs\/2311.05864"},{"key":"e_1_3_2_31_2","unstructured":"Shuyuan Xu Jianchao Ji Yunqi Li Yingqiang Ge Juntao Tan and Yongfeng Zhang. 2023. Causal inference for recommendation: Foundations methods and applications. arXiv:2301.04016. Retrieved from https:\/\/arxiv.org\/abs\/2301.04016"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3606035"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3054782"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3290140"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3490593"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"e_1_3_2_37_2","first-page":"7154","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Yu Yue","year":"2019","unstructured":"Yue Yu, Jie Chen, Tian Gao, and Mo Yu. 2019. DAG-GNN: DAG structure learning with graph neural networks. In Proceedings of the 36th International Conference on Machine Learning. Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.), PMLR, 7154\u20137163. Retrieved from https:\/\/proceedings.mlr.press\/v97\/yu19a.html"},{"key":"e_1_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Qing Zhang Xiaoying Zhang Yang Liu Hongning Wang Min Gao Jiheng Zhang and Ruocheng Guo. 2023. Debiasing recommendation by learning identifiable latent confounders. arXiv:2302.05052. Retrieved from https:\/\/arxiv.org\/abs\/2302.05052","DOI":"10.1145\/3580305.3599296"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247563"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462875"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557680"},{"key":"e_1_3_2_42_2","unstructured":"Xun Zheng Bryon Aragam Pradeep Ravikumar and Eric P. Xing. 2018. DAGs with NO TEARS: Continuous optimization for structure learning. arXiv:1803.01422. Retrieved from https:\/\/arxiv.org\/abs\/1803.01422"},{"key":"e_1_3_2_43_2","unstructured":"Xinyuan Zhu Yang Zhang Fuli Feng Xun Yang Dingxian Wang and Xiangnan He. 2022. Mitigating hidden confounding effects for causal recommendation. arXiv:2205.07499. Retrieved from https:\/\/arxiv.org\/abs\/2205.07499"},{"key":"e_1_3_2_44_2","unstructured":"Yaochen Zhu Jing Yi Jiayi Xie and Zhenzhong Chen. 2022. Deep Causal Reasoning for Recommendations. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:245769824"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T16:13:14Z","timestamp":1757520794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731447"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3731447"],"URL":"https:\/\/doi.org\/10.1145\/3731447","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"assertion":[{"value":"2024-08-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}