Deep Causal Reasoning for Recommendations
Article No.: 68, Pages 1 - 25
Abstract
Traditional recommender systems aim to estimate a user’s rating to an item based on observed ratings from the population. As with all observational studies, hidden confounders, which are factors that affect both item exposures and user ratings, lead to a systematic bias in the estimation. Consequently, causal inference has been introduced in recommendations to address the influence of unobserved confounders. Observing that confounders in recommendations are usually shared among items and are therefore multi-cause confounders, we model the recommendation as a multi-cause multi-outcome (MCMO) inference problem. Specifically, to remedy the confounding bias, we estimate user-specific latent variables that render the item exposures independent Bernoulli trials. The generative distribution is parameterized by a DNN with factorized logistic likelihood and the intractable posteriors are estimated by variational inference. Controlling these factors as substitute confounders, under mild assumptions, can eliminate the bias incurred by multi-cause confounders. Furthermore, we show that MCMO modeling may lead to high variance due to scarce observations associated with the high-dimensional treatment space. Therefore, we theoretically demonstrate that controlling user features as pre-treatment variables can substantially improve sample efficiency and alleviate overfitting. Empirical studies on both simulated and real-world datasets demonstrate that the proposed deep causal recommender shows more robustness to unobserved confounders than state-of-the-art causal recommenders. Codes and datasets are released at https://github.com/yaochenzhu/Deep-Deconf.
References
[1]
Stephen Bonner and Flavian Vasile. 2018. Causal embeddings for recommendation. In Proceedings of the 12th ACM Conference on Recommender Systems. 104–112.
[2]
Djallel Bouneffouf, Amel Bouzeghoub, and Alda Lopes Gançarski. 2012. A contextual-bandit algorithm for mobile context-aware recommender system. In Proceedings of International Conference on Neural Information Processing. Springer, 324–331.
[3]
Jianxin Chang, Chen Gao, Xiangnan He, Depeng Jin, and Yong Li. 2023. Bundle recommendation and generation with graph neural networks. IEEE Trans. Knowl. Data Eng. 25, 3 (2023), 2326–2340.
[4]
Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, and Xiangnan He. 2023. Bias and debias in recommender system: A survey and future directions. ACM Trans. Inf. Syst. 41, 3 (2023), 1–39.
[5]
Jiawei Chen, Yan Feng, Martin Ester, Sheng Zhou, Chun Chen, and Can Wang. 2018. Modeling users’ exposure with social knowledge influence and consumption influence for recommendation. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 953–962.
[6]
Maurizio Ferrari Dacrema, Paolo Cremonesi, and Dietmar Jannach. 2019. Are we really making much progress? A worrying analysis of recent neural recommendation approaches. In Proceedings of the 13th ACM Conference on Recommender Systems. 101–109.
[7]
Alexander D’Amour. 2019. On multi-cause causal inference with unobserved confounding: Counterexamples, impossibility, and alternatives. Retrieved from https://arXiv:1902.10286.
[8]
Sihao Ding, Peng Wu, Fuli Feng, Yitong Wang, Xiangnan He, Yong Liao, and Yongdong Zhang. 2022. Addressing unmeasured confounder for recommendation with sensitivity analysis. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 305–315.
[9]
Chongming Gao, Shijun Li, Yuan Zhang, Jiawei Chen, Biao Li, Wenqiang Lei, Peng Jiang, and Xiangnan He. 2022. KuaiRand: An unbiased sequential recommendation dataset with randomly exposed videos. In Proceedings of the 31st ACM International Conference on Information and Knowledge Management. 3953–3957.
[10]
Junruo Gao, Mengyue Yang, Yuyang Liu, and Jun Li. 2021. Deconfounding representation learning based on user interactions in recommendation systems. In Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 588–599.
[11]
Wenshuo Guo, Serena Wang, Peng Ding, Yixin Wang, and Michael I. Jordan. 2021. Multi-source causal inference using control variates. Retrieved from https://arxiv.org/abs/2103.16689.
[12]
Xiangnan He, Yang Zhang, Fuli Feng, Chonggang Song, Lingling Yi, Guohui Ling, and Yongdong Zhang. 2023. Addressing confounding feature issue for causal recommendation. ACM Trans. Inf. Syst. 41, 3 (2023), 1–23.
[13]
Paul W Holland. 1986. Statistics and causal inference. J. Amer. Statist. Assoc. 81, 396 (1986), 945–960.
[14]
Yifan Hu, Yehuda Koren, and Chris Volinsky. 2008. Collaborative filtering for implicit feedback datasets. In Proceedings of the 8th IEEE International Conference on Data Mining. 263–272.
[15]
Kosuke Imai and David A Van Dyk. 2004. Causal inference with general treatment regimes: Generalizing the propensity score. J. Amer. Statist. Assoc. 99, 467 (2004), 854–866.
[16]
Guido W Imbens and Donald B Rubin. 2015. Causal Inference in Statistics, Social, and Biomedical Sciences. Cambridge University Press.
[17]
Thorsten Joachims, Adith Swaminathan, and Tobias Schnabel. 2017. Unbiased learning-to-rank with biased feedback. In Proceedings of the 10th ACM International Conference on Web Search and Data Mining. 781–789.
[18]
Richard Arnold Johnson, Dean W. Wichern et al. 2002. Multivariate linear regression models. In Applied Multivariate Statistical Analysis. Chapter 7, 360–417.
[19]
Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations.
[20]
Diederik P. Kingma and Max Welling. 2013. Auto-encoding variational Bayes. In Proceedings of the International Conference on Learning Representations.
[21]
Yehuda Koren. 2008. Factorization meets the neighborhood: A multifaceted collaborative filtering model. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 426–434.
[22]
Haoxuan Li, Yanghao Xiao, Chunyuan Zheng, and Peng Wu. 2023. Balancing unobserved confounding with a few unbiased ratings in debiased recommendations. In Proceedings of the ACM Web Conference 2023. 1305–1313.
[23]
Yunqi Li, Hanxiong Chen, Shuyuan Xu, Yingqiang Ge, Juntao Tan, Shuchang Liu, and Yongfeng Zhang. 2022. Fairness in recommendation: A survey. Retrieved from https://arXiv:2205.13619.
[24]
Dawen Liang, Rahul G. Krishnan, Matthew D. Hoffman, and Tony Jebara. 2018. Variational autoencoders for collaborative filtering. In Proceedings of the World Wide Web Conference. 689–698.
[25]
Dawen Liang, Minshu Zhan, and Daniel P. W. Ellis. 2015. Content-aware collaborative music recommendation using pre-trained neural networks. In Proceedings of the Annual Conference of the International Society for Music Information Retrieval. 295–301.
[26]
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 Proceedings of the 15th ACM Conference on Recommender Systems. 351–360.
[27]
Christos Louizos, Uri Shalit, Joris Mooij, David Sontag, Richard Zemel, and Max Welling. 2017. Causal effect inference with deep latent-variable models. In Proceedings of the 31st International Conference on Neural Information Processing Systems (2017).
[28]
Yunan Luo, Jian Peng, and Jianzhu Ma. 2020. When causal inference meets deep learning. Nature Mach. Intell. 2, 8 (2020), 426–427.
[29]
Jing Ma, Ruocheng Guo, Aidong Zhang, and Jundong Li. 2021. Multi-cause effect estimation with disentangled confounder representation. In Proceedings of the 13th International Joint Conference on Artificial Intelligence.
[30]
Jing Ma, Mengting Wan, Longqi Yang, Jundong Li, Brent Hecht, and Jaime Teevan. 2022. Learning causal effects on hypergraphs. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1202–1212.
[31]
Benjamin M. Marlin and Richard S. Zemel. 2009. Collaborative prediction and ranking with non-random missing data. In Proceedings of the 3rd ACM Conference on Recommender Systems. 5–12.
[32]
Elizabeth L. Ogburn, Ilya Shpitser, and Eric J. Tchetgen Tchetgen. 2019. Comment on “blessings of multiple causes.” J. Amer. Statist. Assoc. 114, 528 (2019), 1611–1615.
[33]
Nick Pawlowski, Daniel Coelho de Castro, and Ben Glocker. 2020. Deep structural causal models for tractable counterfactual inference. In Proceedings of the International Conference on Neural Information Processing System.
[34]
Judea Pearl, Madelyn Glymour, and Nicholas P. Jewell. 2016. Causal Inference in Statistics: A Primer. John Wiley & Sons.
[35]
Bruno Pradel, Nicolas Usunier, and Patrick Gallinari. 2012. Ranking with non-random missing ratings: Influence of popularity and positivity on evaluation metrics. In Proceedings of the 6th ACM Conference on Recommender Systems. 147–154.
[36]
Vineeth Rakesh, Ruocheng Guo, Raha Moraffah, Nitin Agarwal, and Huan Liu. 2018. Linked causal variational autoencoder for inferring paired spillover effects. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 1679–1682.
[37]
Donald B. Rubin. 1984. Bayesianly justifiable and relevant frequency calculations for the applies statistician. Ann. Stat. 12, 4 (1984), 1151–1172.
[38]
Donald B. Rubin. 1990. Formal model of statistical inference for causal effects. J. Stat. Plan. Infer. 25, 3 (1990), 279–292.
[39]
Ruslan Salakhutdinov and Nathan Srebro. 2010. Collaborative filtering in a non-uniform world: Learning with the weighted trace norm. In Proceedings of the International Conference on Neural Information Processing System. 2056–2064.
[40]
Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as treatments: Debiasing learning and evaluation. In Proceedings of the International Conference on Machine Learning. 1670–1679.
[41]
Bernhard Scholkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, and Yoshua Bengio. 2021. Toward causal representation learning. Proc. IEEE 109, 5 (2021), 612–634.
[42]
Harald Steck. 2010. Training and testing of recommender systems on data missing not at random. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 713–722.
[43]
Harald Steck. 2011. Item popularity and recommendation accuracy. In Proceedings of the 5th ACM Conference on Recommender Systems. 125–132.
[44]
Harald Steck. 2013. Evaluation of recommendations: Rating-prediction and ranking. In Proceedings of the 7th ACM Conference on Recommender Systems. 213–220.
[45]
Juntao Tan, Shuyuan Xu, Yingqiang Ge, Yunqi Li, Xu Chen, and Yongfeng Zhang. 2021. Counterfactual explainable recommendation. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management. 1784–1793.
[46]
Yixin Wang and David M. Blei. 2019. The blessings of multiple causes. J. Amer. Statist. Assoc. 114, 528 (2019), 1574–1596.
[47]
Yixin Wang and David M. Blei. 2020. Towards clarifying the theory of the deconfounder. Retrieved from https://arXiv:2003.04948.
[48]
Yixin Wang, Dawen Liang, Laurent Charlin, and David M. Blei. 2020. Causal inference for recommender systems. In Proceedings of the 14th ACM Conference on Recommender Systems. 426–431.
[49]
Tianxin Wei, Fuli Feng, Jiawei Chen, Ziwei Wu, Jinfeng Yi, and Xiangnan He. 2021. Model-agnostic counterfactual reasoning for eliminating popularity bias in recommender system. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1791–1800.
[50]
Le Wu, Qi Liu, Enhong Chen, Nicholas Jing Yuan, Guangming Guo, and Xing Xie. 2016. Relevance meets coverage: A unified framework to generate diversified recommendations. ACM Trans. Intell. Syst. Technol. 7, 3 (2016), 1–30.
[51]
Teng Xiao and Suhang Wang. 2022. Towards unbiased and robust causal ranking for recommender systems. In Proceedings of the 15th ACM International Conference on Web Search and Data Mining. 1158–1167.
[52]
Chenxiao Xu, Hao Huang, and Shinjae Yoo. 2019. Scalable causal graph learning through a deep neural network. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 1853–1862.
[53]
Shuyuan Xu, Juntao Tan, Shelby Heinecke, Vena Jia Li, and Yongfeng Zhang. 2023. Deconfounded causal collaborative filtering. ACM Trans. Rec. Syst. 1, 4 (2023), 1–25.
[54]
Mengyue Yang, Quanyu Dai, Zhenhua Dong, Xu Chen, Xiuqiang He, and Jun Wang. 2021. Top-n recommendation with counterfactual user preference simulation. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management. 2342–2351.
[55]
Shuai Yang, Xianjie Guo, Kui Yu, Xiaoling Huang, Tingting Jiang, Jin He, and Lichuan Gu. 2023. Causal feature selection in the presence of sample selection bias. ACM Trans. Intell. Syst. Technol. 14, 5 (2023), 1–18.
[56]
Jingsen Zhang, Xu Chen, and Wayne Xin Zhao. 2021. Causally attentive collaborative filtering. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management. 3622–3626.
[57]
Yang Zhang, Fuli Feng, Xiangnan He, Tianxin Wei, Chonggang Song, Guohui Ling, and Yongdong Zhang. 2021. Causal intervention for leveraging popularity bias in recommendation. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 11–20.
[58]
Minghao Zhao, Qilin Deng, Kai Wang, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen, and Peng Cui. 2021. Bilateral filtering graph convolutional network for multi-relational social recommendation in the power-law networks. ACM Trans. Inf. Syst. 40, 2 (2021), 1–24.
[59]
Xiaolin Zheng, Menghan Wang, Renjun Xu, Jianmeng Li, and Yan Wang. 2020. Modeling dynamic missingness of implicit feedback for sequential recommendation. IEEE Trans. Knowl. Data Eng. 34, 1 (2020), 405–418.
[60]
Yu Zheng, Chen Gao, Xiang Li, Xiangnan He, Yong Li, and Depeng Jin. 2021. Disentangling user interest and conformity for recommendation with causal embedding. In Proceedings of the Web Conference. 2980–2991.
[61]
Yaochen Zhu, Jing Ma, and Jundong Li. 2023. Causal inference and recommendations. In Machine Learning for Causal Inference. Springer, 207–245.
[62]
Yaochen Zhu, Jing Ma, and Jundong Li. 2023. Causal inference in recommender systems: A survey of strategies for bias mitigation, explanation, and generalization. Retrieved from https://arXiv:2301.00910.
[63]
Hao Zou, Peng Cui, Bo Li, Zheyan Shen, Jianxin Ma, Hongxia Yang, and Yue He. 2020. Counterfactual prediction for bundle treatment. Proc. Adv. Neural Inf. Process. Syst. 33 (2020).
Index Terms
- Deep Causal Reasoning for Recommendations
Recommendations
Causal Inference for Recommender Systems
RecSys '20: Proceedings of the 14th ACM Conference on Recommender SystemsThe task of recommender systems is classically framed as a prediction of users’ preferences and users’ ratings. However, its spirit is to answer a counterfactual question: “What would the rating be if we ‘forced’ the user to watch the movie?” This is a ...
Collaborative Variational Autoencoder for Recommender Systems
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningModern recommender systems usually employ collaborative filtering with rating information to recommend items to users due to its successful performance. However, because of the drawbacks of collaborative-based methods such as sparsity, cold start, etc., ...
Mitigating Confounding Bias for Recommendation via Counterfactual Inference
Machine Learning and Knowledge Discovery in DatabasesAbstractRecommender systems usually face the bias problem, which creates a gap between recommendation results and the actual user preference. Existing works track this problem by assuming a specific bias and then develop a method to mitigate it, which ...
Comments
Information & Contributors
Information
Published In
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 18 June 2024
Online AM: 26 March 2024
Accepted: 26 February 2024
Revised: 31 December 2023
Received: 11 July 2023
Published in TIST Volume 15, Issue 4
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Natural Science Foundation of China
- Tencent
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 429Total Downloads
- Downloads (Last 12 months)429
- Downloads (Last 6 weeks)51
Reflects downloads up to 10 Feb 2025
Other Metrics
Citations
Cited By
View allView Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in