Fangyuan Luo
ABSTRACT
In recommender systems (RSs), inverse propensity score (IPS) has been a key technique to mitigate popularity bias by decreasing the contribution of popular items in modeling user-item interactions. However, conventional IPS treats all users equally, which tends to over-debias the popularity-insensitive (PI) users and under-debias the popularity-sensitive (PS) users. Furthermore, in such a treatment, IPS only performs slightly well on the debiased test while does not work on the normal biased test. To this end, we propose a user-dependent IPS (UDIPS in short) method, which adaptively conducts propensity estimation for each user-item pair based on the user's sensitivity to item popularity. Like IPS, our theoretical analysis validates the unbiasedness of UDIPS. Remarkably, our solution is model-agnostic and can be easily used to upgrade current unbiased recommenders. We implemented it in four state-of-the-art models for unbiased recommendation, and experimental results on two benchmark datasets demonstrate the effectiveness of our method in both unbiased and normal biased test.
Supplemental Material
- Himan Abdollahpouri, Robin Burke, and Bamshad Mobasher. 2019. Managing Popularity Bias in Recommender Systems with Personalized Re-Ranking. In FLAIRS. 413--418.Google Scholar
- Himan Abdollahpouri and Masoud Mansoury. 2020. Multi-sided Exposure Bias in Recommendation. CoRR, Vol. abs/2006.15772 (2020).Google Scholar
- Jiawei Chen, Hande Dong, Yang Qiu, Xiangnan He, Xin Xin, Liang Chen, Guli Lin, and Keping Yang. 2021. AutoDebias: Learning to Debias for Recommendation. In SIGIR. 21--30.Google Scholar
- 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., Vol. 41, 3 (2023), 39.Google ScholarDigital Library
- Sihao Ding, Fuli Feng, Xiangnan He, Jinqiu Jin, Wenjie Wang, Yong Liao, and Yongdong Zhang. 2022. Interpolative Distillation for Unifying Biased and Debiased Recommendation. In SIGIR. 40--49.Google Scholar
- Alois Gruson, Praveen Chandar, Christophe Charbuillet, James McInerney, Samantha Hansen, Damien Tardieu, and Ben Carterette. 2019. Offline Evaluation to Make Decisions About PlaylistRecommendation Algorithms. In WSDM. 420--428.Google Scholar
- 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 WSDM. 381--389.Google Scholar
- Thorsten Joachims, Adith Swaminathan, and Tobias Schnabel. 2017. Unbiased Learning-to-Rank with Biased Feedback. In WSDM. 781--789.Google Scholar
- Dugang Liu, Pengxiang Cheng, Zhenhua Dong, Xiuqiang He, Weike Pan, and Zhong Ming. 2020. A General Knowledge Distillation Framework for Counterfactual Recommendation via Uniform Data. In SIGIR. 831--840.Google Scholar
- Wondo Rhee, Sung Min Cho, and Bongwon Suh. 2022. Countering Popularity Bias by Regularizing Score Differences. In RecSys. 145--155.Google Scholar
- Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as Treatments: Debiasing Learning and Evaluation. In ICML, Vol. 48. 1670--1679.Google Scholar
- Wenjie Wang, Fuli Feng, Xiangnan He, Xiang Wang, and Tat-Seng Chua. 2021. Deconfounded Recommendation for Alleviating Bias Amplification. In KDD. 1717--1725.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, Vol. 97. 6638--6647.Google Scholar
- 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 KDD. 1791--1800.Google Scholar
- Guipeng Xv, Chen Lin, Hui Li, Jinsong Su, Weiyao Ye, and Yewang Chen. 2022. Neutralizing Popularity Bias in Recommendation Models. In SIGIR. 2623--2628.Google Scholar
- Longqi Yang, Yin Cui, Yuan Xuan, Chenyang Wang, Serge J. Belongie, and Deborah Estrin. 2018. Unbiased offline recommender evaluation for missing-not-at-random implicit feedback. In RecSys. 279--287.Google Scholar
- Mi Zhang and Neil Hurley. 2008. Avoiding monotony: improving the diversity of recommendation lists. In RecSys. 123--130.Google Scholar
- 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 SIGIR. 11--20.Google Scholar
- Ziwei Zhu, Yun He, Xing Zhao, Yin Zhang, Jianling Wang, and James Caverlee. 2021. Popularity-Opportunity Bias in Collaborative Filtering. In WSDM. 85--93.Google Scholar
Index Terms
- User-Dependent Learning to Debias for Recommendation
Recommendations
Causal Intervention for Leveraging Popularity Bias in Recommendation
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalRecommender system usually faces popularity bias issues: from the data perspective, items exhibit uneven (usually long-tail) distribution on the interaction frequency; from the method perspective, collaborative filtering methods are prone to amplify the ...
SGCCL: Siamese Graph Contrastive Consensus Learning for Personalized Recommendation
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data MiningContrastive-learning-based neural networks have recently been introduced to recommender systems, due to their unique advantage of injecting collaborative signals to model deep representations, and the self-supervision nature in the learning process. ...
An optimized recommendation framework exploiting textual review based opinion mining for generating pleasantly surprising, novel yet relevant recommendations
Highlights- Building user preferences using review-based opinion mining and rating information.
AbstractSerendipity is a critical factor in the Recommender Systems (RS) in delivering pleasantly surprising, novel, yet contextually relevant recommendations. Most existing methods improve serendipity in RS by learning user preferences based ...
Comments