Wenjie Wang
Xiangnan He
ABSTRACT
Data-driven recommender systems have demonstrated great success in various Web applications owing to the extraordinary ability of machine learning models to recognize patterns (ie correlation) from users' behaviors. However, they still suffer from several issues such as biases and unfairness due to spurious correlations. Considering the causal mechanism behind data can avoid the influences of such spurious correlations. In this light, embracing causal recommender modeling is an exciting and promising direction.
In this tutorial, we aim to introduce the key concepts in causality and provide a systemic review of existing work on causal recommendation. We will introduce existing methods from two different causal frameworks --- the potential outcome (PO) framework and the structural causal model (SCM). We will give examples and discussions regarding how to utilize different causal tools under these two frameworks to model and solve problems in recommendation. Moreover, we will summarize and compare the paradigms of PO-based and SCM-based recommendation. Besides, we identify some open challenges and potential future directions for this area. We hope this tutorial could stimulate more ideas on this topic and facilitate the development of causality-aware recommender systems.
- Heejung Bang and James M. Robins. 2005. Doubly robust estimation in missing data and causal inference models. Biometrics, Vol. 61 (2005), 962--972.Google Scholar
Cross Ref
- Gang Chen, Jiawei Chen, Fuli Feng, Sheng Zhou, and Xiangnan He. 2023. Unbiased Knowledge Distillation for Recommendation. In WSDM. 976--984.Google Scholar
- Jiawei Chen, Hande Dong, Yang Qiu, Xiangnan He, Xin Xin, Liang Chen, Guli Lin, and Keping Yang. 2021a. AutoDebias: Learning to Debias for Recommendation. In SIGIR. 21--30.Google Scholar
- Jiawei Chen, Xiang Wang, Fuli Feng, and Xiangnan He. 2021b. Bias Issues and Solutions in Recommender System. In RecSys. 825--827.Google Scholar
- Quanyu Dai, Haoxuan Li, Peng Wu, Zhenhua Dong, Xiao-Hua Zhou, Rui Zhang, Rui Zhang, and Jie Sun. 2022. A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Prediction. In KDD. 252--262.Google Scholar
- Sihao Ding, Fuli Feng, Xiangnan He, Yong Liao, Jun Shi, and Yongdong Zhang. 2021. Causal incremental graph convolution for recommender system retraining. TNNLS (2021).Google Scholar
- 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 KDD. 305--315.Google Scholar
- Chongming Gao, Wenqiang Lei, Jiawei Chen, Shiqi Wang, Xiangnan He, Shijun Li, Biao Li, Yuan Zhang, and Peng Jiang. 2023. CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System. TOIS (2023).Google Scholar
- Chen Gao, Yu Zheng, Wenjie Wang, Fuli Feng, Xiangnan He, and Yong Li. 2022. Causal Inference in Recommender Systems: A Survey and Future Directions. arXiv preprint 2208.12397 (2022).Google Scholar
- Ming He, Xin Chen, Xinlei Hu, and Changshu Li. 2022a. Causal Intervention for Sentiment De-biasing in Recommendation. In PCIKM. ACM, 4014--4018.Google Scholar
- Xiangnan He, Yang Zhang, Fuli Feng, Chonggang Song, Lingling Yi, Guohui Ling, and Yongdong Zhang. 2022b. Addressing Confounding Feature Issue for Causal Recommendation. TOIS (2022).Google Scholar
- José Miguel Hernández-Lobato, Neil Houlsby, and Zoubin Ghahramani. 2014. Probabilistic matrix factorization with non-random missing data. In ICML.Google Scholar
- Daniel G Horvitz and Donovan J Thompson. 1952. A generalization of sampling without replacement from a finite universe. JASA, Vol. 47 (1952), 663--685.Google ScholarCross Ref
- Wenjie Hu, Xiaohua Zhou, and Peng Wu. 2022. Identification and estimation of treatment effects on long-term outcomes in clinical trials with external observational data. arXiv:2208.10163 (2022).Google Scholar
- Olivier Jeunen, Thorsten Joachims, Harrie Oosterhuis, Yuta Saito, and Flavian Vasile. 2022. CONSEQUENCES-Causality, Counterfactuals and Sequential Decision-Making for Recommender Systems. In RecSys. 654--657.Google Scholar
- Haoxuan Li, Quanyu Dai, Yuru Li, Yan Lyu, Zhenhua Dong, Xiao-Hua Zhou, and Peng Wu. 2023 a. Multiple Robust Learning for Recommendation. In AAAI.Google Scholar
- Haoxuan Li, Yan Lyu, Chunyuan Zheng, and Peng Wu. 2023 b. TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendations. In ICLR.Google Scholar
- Haoxuan Li, Yanghao Xiao, Chunyuan Zheng, and Peng Wu. 2023 c. Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations. In WWW.Google Scholar
- Haoxuan Li, Yanghao Xiao, Chunyuan Zheng, Peng Wu, and Peng Cui. 2023 d. Propensity Matters: Measuring and Enhancing Balancing for Recommendation. In ICML.Google Scholar
- Haoxuan Li, Chunyuan Zheng, Yixiao Cao, Zhi Geng, Yue Liu, and Peng Wu. 2023 f. Trustworthy Policy Learning under the Counterfactual No-Harm Criterion. In ICML.Google Scholar
- Haoxuan Li, Chunyuan Zheng, and Peng Wu. 2023 e. StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random. In ICLR.Google Scholar
- Haoxuan Li, Chunyuan Zheng, Peng Wu, Kun Kuang, Yue Liu, and Peng Cui. 2023 g. Who should be Given Incentives? Counterfactual Optimal Treatment Regimes Learning for Recommendation.Google Scholar
- Yunqi Li, Hanxiong Chen, Shuyuan Xu, Yingqiang Ge, and Yongfeng Zhang. 2021. Towards Personalized Fairness Based on Causal Notion. In SIGIR. 1054--1063.Google Scholar
- Dugang Liu, Pengxiang Cheng, Zinan Lin, Jinwei Luo, Zhenhua Dong, Xiuqiang He, Weike Pan, and Zhong Ming. 2022. KDCRec: Knowledge Distillation for Counterfactual Recommendation Via Uniform Data. TKDE (2022).Google Scholar
- Geert Molenberghs, Garrett Fitzmaurice, Michael G. Kenward, Anastasios Tsiatis, and Geert Verbeke. 2015. Handbook of Missing Data Methodology.Google Scholar
- Shanlei Mu, Yaliang Li, Wayne Xin Zhao, Jingyuan Wang, Bolin Ding, and Ji-Rong Wen. 2022. Alleviating Spurious Correlations in Knowledge-Aware Recommendations through Counterfactual Generator. In SIGIR. 1401--1411.Google Scholar
- Judea Pearl. 2009. Causality. Cambridge university press.Google Scholar
- D. B. Rubin. 1974. Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of educational psychology, Vol. 66 (1974), 688--701.Google ScholarCross Ref
- Yuta Saito and Thorsten Joachims. 2022. Counterfactual Evaluation and Learning for Interactive Systems: Foundations, Implementations, and Recent Advances. In SIGKDD. 4824--4825.Google Scholar
- Yuta Saito, Suguru Yaginuma, Yuta Nishino, Hayato Sakata, and Kazuhide Nakata. 2020. Unbiased recommender learning from missing-not-at-random implicit feedback. In WSDM. 501--509.Google Scholar
- Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as treatments: Debiasing learning and evaluation. In ICML. 1670--1679.Google Scholar
- Harald Steck. 2010. Training and testing of recommender systems on data missing not at random. In SIGKDD.Google Scholar
- Adith Swaminathan and Thorsten Joachims. 2015. The Self-Normalized Estimator for Counterfactual Learning. In NIPS.Google Scholar
- Khanh Hiep Tran, Azin Ghazimatin, and Rishiraj Saha Roy. 2021. Counterfactual Explanations for Neural Recommenders. In SIGIR. 1627--1631.Google Scholar
- Mark J. van der Laan and Sherri Rose. 2011. Targeted Learning: Causal Inference for Observational and Experimental Data. Springer.Google Scholar
- Wenjie Wang, Fuli Feng, Xiangnan He, Xiang Wang, and Tat-Seng Chua. 2021a. Deconfounded Recommendation for Alleviating Bias Amplification. In SIGKDD. 1717--1725.Google Scholar
- Wenjie Wang, Fuli Feng, Xiangnan He, Hanwang Zhang, and Tat-Seng Chua. 2021b. Clicks Can Be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue. In SIGIR. 1288--1297.Google Scholar
- Wenjie Wang, Fuli Feng, Liqiang Nie, and Tat-Seng Chua. 2022a. User-Controllable Recommendation Against Filter Bubbles. In SIGIR. 1251--1261.Google Scholar
- Wenjie Wang, Xinyu Lin, Fuli Feng, Xiangnan He, Min Lin, and Tat-Seng Chua. 2022b. Causal Representation Learning for Out-of-Distribution Recommendation. In WWW. ACM, 3562--3571.Google Scholar
- Wenjie Wang, Xinyu Lin, Liuhui Wang, Fuli Feng, Yunshan Ma, and Tat-Seng Chua. 2023. Causal Disentangled Recommendation Against User Preference Shifts. TOIS (2023).Google Scholar
- Xiaojie Wang, Rui Zhang, Yu Sun, and Jianzhong Qi. 2019. Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random. In ICML. 6638--6647.Google Scholar
- Xiaojie Wang, Rui Zhang, Yu Sun, and Jianzhong Qi. 2021c. Combating Selection Biases in Recommender Systems with a Few Unbiased Ratings. In WSDM.Google Scholar
- Yixin Wang, Dawen Liang, Laurent Charlin, and David M Blei. 2020. Causal inference for recommender systems. In RecSys. 426--431.Google Scholar
- Zhenlei Wang, Shiqi Shen, Zhipeng Wang, Bo Chen, Xu Chen, and Ji-Rong Wen. 2022c. Unbiased Sequential Recommendation with Latent Confounders. In WWW.Google Scholar
- Zhenlei Wang, Jingsen Zhang, Hongteng Xu, Xu Chen, Yongfeng Zhang, Wayne Xin Zhao, and Ji-Rong Wen. 2021d. Counterfactual data-augmented sequential recommendation. In SIGIR. 347--356.Google ScholarDigital Library
- 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 SIGKDD. 1791--1800.Google Scholar
- Peng Wu, ShaSha Han, Xingwei Tong, and Runze Li. 2022a. Propensity score regression for causal inference with treatment heterogeneity. Statistica Sinica (2022).Google Scholar
- Peng Wu, Haoxuan Li, Yuhao Deng, Wenjie Hu, Quanyu Dai, Zhenhua Dong, Jie Sun, Rui Zhang, and Xiao-Hua Zhou. 2022b. On the Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challenges. In IJCAI.Google Scholar
- Peng Wu, Zhiqiang Tan, Wenjie Hu, and Xiao-Hua Zhou. 2022c. Model-Assisted Inference for Covariate-Specific Treatment Effects with High-dimensional Data. Statistica Sinica (2022).Google Scholar
- Peng Wu, Xinyi Xu, Xingwei Tong, Qing Jiang, and Bo Lu. 2021. Semiparametric estimation for average causal effects using propensity score-based spline. Journal of Statistical Planning and Inference, Vol. 212 (2021), 153--168.Google ScholarCross Ref
- Bowen Yuan, Jui-Yang Hsia, Meng-Yuan Yang, Hong Zhu, Chih-Yao Chang, Zhenhua Dong, and Chih-Jen Lin. 2019. Improving ad click prediction by considering non-displayed events. In CIKM. 329--338.Google Scholar
- Ruohan Zhan, Changhua Pei, Qiang Su, Jianfeng Wen, Xueliang Wang, Guanyu Mu, Dong Zheng, Peng Jiang, and Kun Gai. 2022. Deconfounding Duration Bias in Watch-Time Prediction for Video Recommendation. In KDD. ACM, 4472--4481.Google Scholar
- Wenhao Zhang, Wentian Bao, Xiao-Yang Liu, Keping Yang, Quan Lin, Hong Wen, and Ramin Ramezani. 2020. Large-scale Causal Approaches to Debiasing Post-click Conversion Rate Estimation with Multi-task Learning. In WWW.Google Scholar
- Yongfeng Zhang, Xu Chen, Yi Zhang, and Xianjie Chen. 2021a. CSR 2021: The 1st International Workshop on Causality in Search and Recommendation. In SIGIR.Google Scholar
- Yang Zhang, Fuli Feng, Xiangnan He, Tianxin Wei, Chonggang Song, Guohui Ling, and Yongdong Zhang. 2021b. Causal Intervention for Leveraging Popularity Bias in Recommendation. In SIGIR. 11--20.Google Scholar
- Yang Zhang, Wenjie Wang, Peng Wu, Fuli Feng, and Xiangnan He. 2022. Causal Recommendation: Progresses and Future Directions. In WWW.Google Scholar
- Zihao Zhao, Jiawei Chen, Sheng Zhou, Xiangnan He, Xuezhi Cao, Fuzheng Zhang, and Wei Wu. 2022. Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation. TKDE (2022).Google Scholar
- 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 WWW. 2980--2991.Google Scholar
- Xinyuan Zhu, Yang Zhang, Fuli Feng, Xun Yang, Dingxian Wang, and Xiangnan He. 2022. Mitigating Hidden Confounding Effects for Causal Recommendation. arXiv (2022).Google Scholar
Index Terms
- Causal Recommendation: Progresses and Future Directions
Recommendations
Towards Trustworthy Recommender System: A Faithful and Responsible Recommendation Perspective
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalRecommender systems (RecSys) become increasingly prevalent in modern society, offering personalized information filtering to alleviate information overload and significantly impacting various human online activities. Machine learning-based recommendation ...
Causal Inference in Recommender Systems: A Survey and Future Directions
Recommender systems have become crucial in information filtering nowadays. Existing recommender systems extract user preferences based on the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature, or feature-...
Causal embeddings for recommendation
RecSys '18: Proceedings of the 12th ACM Conference on Recommender SystemsMany current applications use recommendations in order to modify the natural user behavior, such as to increase the number of sales or the time spent on a website. This results in a gap between the final recommendation objective and the classical setup ...
Comments