ABSTRACT
Recommender system (RS) is widely applied in a multitude of scenarios to aid individuals obtaining the information they require efficiently. At the same time, the prevalence of popularity bias in such systems has become a widely acknowledged issue. To address this challenge, we propose a novel method named Model-Agnostic Popularity Debias Training Framework (MDTF). It consists of two basic modules including 1) General Ranking Model (GRM), which is model-agnostic and can be implemented as any ranking models; and 2) Popularity Debias Module (PDM), which estimates the impact of the competitiveness and popularity of candidate items on the CTR, by utilizing the feedback of cold-start users to re-weigh the loss in GRM. MDTF seamlessly integrates these two modules in an end-to-end multi-task learning framework. Extensive experiments on both real-world offline dataset and online A/B test demonstrate its superiority over state-of-the-art methods.
Supplemental Material
- Himan Abdollahpouri, Robin Burke, and Bamshad Mobasher. 2017. Controlling popularity bias in learning-to-rank recommendation. In Proceedings of the eleventh ACM conference on recommender systems. 42--46.Google ScholarDigital Library
- Rounak Banik. 2017. The Movies Dataset. https://www.kaggle.com/datasets/rounakbanik/the-movies-dataset Retrieved April 25, 2023 fromGoogle Scholar
- James Bennett, Stan Lanning, et al. 2007. The netflix prize. In Proceedings of KDD cup and workshop, Vol. 2007. New York, 35.Google Scholar
- Stephen Bonner and Flavian Vasile. 2018. Causal embeddings for recommendation. In Proceedings of the 12th ACM conference on recommender systems. 104--112.Google ScholarDigital Library
- Roc'io Ca namares and Pablo Castells. 2018. Should I follow the crowd? A probabilistic analysis of the effectiveness of popularity in recommender systems. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 415--424.Google Scholar
- Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, and Xiangnan He. 2020a. Bias and debias in recommender system: A survey and future directions. ACM Transactions on Information Systems (2020).Google Scholar
- Zhihong Chen, Rong Xiao, Chenliang Li, Gangfeng Ye, Haochuan Sun, and Hongbo Deng. 2020b. Esam: Discriminative domain adaptation with non-displayed items to improve long-tail performance. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 579--588.Google ScholarDigital Library
- Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson, Greg Corrado, Wei Chai, Mustafa Ispir, et al. 2016. Wide & deep learning for recommender systems. In Proceedings of the 1st workshop on deep learning for recommender systems. 7--10.Google ScholarDigital Library
- Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, Xiuqiang He, and Zhenhua Dong. 2018. Deepfm: An end-to-end wide & deep learning framework for CTR prediction. arXiv preprint arXiv:1804.04950 (2018).Google Scholar
- Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry Heck. 2013. Learning deep structured semantic models for web search using clickthrough data. In Proceedings of the 22nd ACM international conference on Information & Knowledge Management. 2333--2338.Google ScholarDigital Library
- Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, and Jun Sakuma. 2014. Correcting Popularity Bias by Enhancing Recommendation Neutrality. RecSys Posters, Vol. 805 (2014).Google Scholar
- Yuta Saito. 2019. Unbiased pairwise learning from implicit feedback. In NeurIPS 2019 Workshop on Causal Machine Learning.Google Scholar
- Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as treatments: Debiasing learning and evaluation. In international conference on machine learning. PMLR, 1670--1679.Google Scholar
- Qijie Shen, Wanjie Tao, Jing Zhang, Hong Wen, Zulong Chen, and Quan Lu. 2021. SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 4094--4103.Google ScholarDigital Library
- Qijie Shen, Hong Wen, Wanjie Tao, Jing Zhang, Fuyu Lv, Zulong Chen, and Zhao Li. 2022a. Deep Interest Highlight Network for Click-Through Rate Prediction in Trigger-Induced Recommendation. In Proceedings of the ACM Web Conference 2022. 422--430.Google ScholarDigital Library
- Qijie Shen, Hong Wen, Jing Zhang, and Qi Rao. 2022b. Hierarchically Fusing Long and Short-Term User Interests for Click-Through Rate Prediction in Product Search. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 1767--1776.Google ScholarDigital Library
- 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 2021. 2980--2991.Google ScholarDigital Library
- Guorui Zhou, Xiaoqiang Zhu, Chenru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, and Kun Gai. 2018. Deep interest network for click-through rate prediction. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 1059--1068.Google ScholarDigital Library
- Ziwei Zhu, Yun He, Xing Zhao, Yin Zhang, Jianling Wang, and James Caverlee. 2021. Popularity-opportunity bias in collaborative filtering. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining. 85--93.Google ScholarDigital Library
Index Terms
- A Model-Agnostic Popularity Debias Training Framework for Click-Through Rate Prediction in Recommender System
Recommendations
News Popularity Beyond the Click-Through-Rate for Personalized Recommendations
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalPopularity detection of news articles is critical for making relevant recommendations for users and drive user engagement for maximum business value. Among several well-known metrics such as likes, shares, comments, Click-Through-Rate (CTR) has evolved ...
Multimodal Context-Aware Recommender for Post Popularity Prediction in Social Media
Thematic Workshops '17: Proceedings of the on Thematic Workshops of ACM Multimedia 2017Millions of multimodal posts are uploaded, shared, viewed and liked every day in different social networks, where users express their opinions about different items such as products and places. While, some user posts become popular, others are ignored. ...
Mining Item Popularity for Recommender Systems
ADMA 2013: Part II of the Proceedings of the 9th International Conference on Advanced Data Mining and Applications - Volume 8347Recommender systems can predict individual user's preference individual rating on items by examining similar items' popularity or similar users' taste. However, these systems cannot tell item's long-term popularity . In this paper, we propose an ...
Comments