Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Debiasing Recommendation by Learning Identifiable Latent Confounders (2302.05052v2)

Published 10 Feb 2023 in cs.LG and cs.IR

Abstract: Recommendation systems aim to predict users' feedback on items not exposed to them. Confounding bias arises due to the presence of unmeasured variables (e.g., the socio-economic status of a user) that can affect both a user's exposure and feedback. Existing methods either (1) make untenable assumptions about these unmeasured variables or (2) directly infer latent confounders from users' exposure. However, they cannot guarantee the identification of counterfactual feedback, which can lead to biased predictions. In this work, we propose a novel method, i.e., identifiable deconfounder (iDCF), which leverages a set of proxy variables (e.g., observed user features) to resolve the aforementioned non-identification issue. The proposed iDCF is a general deconfounded recommendation framework that applies proximal causal inference to infer the unmeasured confounders and identify the counterfactual feedback with theoretical guarantees. Extensive experiments on various real-world and synthetic datasets verify the proposed method's effectiveness and robustness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019).
  2. Peter Bühlmann. 2020. Invariance, causality and robustness. Statist. Sci. 35, 3 (2020), 404–426.
  3. Alexander D’Amour. 2019. On multi-cause causal inference with unobserved confounding: Counterexamples, impossibility, and alternatives. arXiv preprint arXiv:1902.10286 (2019).
  4. Addressing Unmeasured Confounder for Recommendation with Sensitivity Analysis. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Washington DC, USA) (KDD ’22). Association for Computing Machinery, New York, NY, USA, 305–315. https://doi.org/10.1145/3534678.3539240
  5. KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 3953–3957.
  6. Na\\\backslash\” ive regression requires weaker assumptions than factor models to adjust for multiple cause confounding. arXiv preprint arXiv:2007.12702 (2020).
  7. Addressing Confounding Feature Issue for Causal Recommendation. arXiv preprint arXiv:2205.06532 (2022).
  8. Miguel A Hernán and James M Robins. 2010. Causal inference.
  9. Variational autoencoders and nonlinear ica: A unifying framework. In International Conference on Artificial Intelligence and Statistics. PMLR, 2207–2217.
  10. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
  11. Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).
  12. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009), 30–37.
  13. J. B. Kruskal. 1989. Rank, Decomposition, and Uniqueness for 3-Way and n-Way Arrays. North-Holland Publishing Co., NLD, 7–18.
  14. Manabu Kuroki and Judea Pearl. 2014. Measurement bias and effect restoration in causal inference. Biometrika 101, 2 (2014), 423–437.
  15. Rating Distribution Calibration for Selection Bias Mitigation in Recommendations. In Proceedings of the ACM Web Conference 2022 (Virtual Event, Lyon, France) (WWW ’22). Association for Computing Machinery, New York, NY, USA, 2048–2057. https://doi.org/10.1145/3485447.3512078
  16. Identifying causal effects with proxy variables of an unmeasured confounder. Biometrika 105, 4 (2018), 987–993.
  17. Identifying effects of multiple treatments in the presence of unmeasured confounding. J. Amer. Statist. Assoc. (2022), 1–15.
  18. A confounding bridge approach for double negative control inference on causal effects. arXiv preprint arXiv:1808.04945 (2018).
  19. ASPIRE: Air Shipping Recommendation for E-Commerce Products via Causal Inference Framework. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Washington DC, USA) (KDD ’22). Association for Computing Machinery, New York, NY, USA, 3584–3592. https://doi.org/10.1145/3534678.3539197
  20. Judea Pearl. 2009. Causality: Models, Reasoning and Inference (2nd ed.). Cambridge University Press.
  21. James Robins. 1986. A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect. Mathematical Modelling 7, 9 (1986), 1393–1512. https://doi.org/10.1016/0270-0255(86)90088-6
  22. Donald B Rubin. 1974. Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of educational Psychology 66, 5 (1974), 688.
  23. Recommendations as treatments: Debiasing learning and evaluation. In international conference on machine learning. PMLR, 1670–1679.
  24. A Model-Agnostic Causal Learning Framework for Recommendation using Search Data. In Proceedings of the ACM Web Conference 2022. 224–233.
  25. Introduction to linear algebra. Vol. 3. Wellesley-Cambridge Press Wellesley, MA.
  26. An introduction to proximal causal learning. arXiv preprint arXiv:2009.10982 (2020).
  27. Deconfounded recommendation for alleviating bias amplification. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1717–1725.
  28. Yixin Wang and David M Blei. 2019. The blessings of multiple causes. J. Amer. Statist. Assoc. 114, 528 (2019), 1574–1596.
  29. Causal inference for recommender systems. In Fourteenth ACM Conference on Recommender Systems. 426–431.
  30. Invariant Preference Learning for General Debiasing in Recommendation. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1969–1978.
  31. Model-agnostic counterfactual reasoning for eliminating popularity bias in recommender system. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1791–1800.
  32. A survey on accuracy-oriented neural recommendation: From collaborative filtering to information-rich recommendation. IEEE Transactions on Knowledge and Data Engineering (2022).
  33. Deconfounded Causal Collaborative Filtering. arXiv preprint arXiv:2110.07122 (2021).
  34. Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 4472–4481.
  35. 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.
  36. Deep interest network for click-through rate prediction. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 1059–1068.
  37. Mitigating Hidden Confounding Effects for Causal Recommendation. arXiv preprint arXiv:2205.07499 (2022).
  38. Deep causal reasoning for recommendations. arXiv preprint arXiv:2201.02088 (2022).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Qing Zhang (138 papers)
  2. Xiaoying Zhang (32 papers)
  3. Yang Liu (2253 papers)
  4. Hongning Wang (107 papers)
  5. Min Gao (81 papers)
  6. Jiheng Zhang (30 papers)
  7. Ruocheng Guo (62 papers)
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now