ABSTRACT
Ranking items regarding individual user interests is a core technique of multiple downstream tasks such as recommender systems. Learning such a personalized ranker typically relies on the implicit feedback from users' past click-through behaviors. However, collected feedback is biased toward previously highly-ranked items and directly learning from it would result in "rich-get-richer" phenomena. In this paper, we propose a simple yet sufficient unbiased learning-to-rank paradigm named InfoRank that aims to simultaneously address both position and popularity biases. We begin by consolidating the impacts of those biases into a single observation factor, thereby providing a unified approach to addressing bias-related issues. Subsequently, we minimize the mutual information between the observation estimation and the relevance estimation conditioned on the input features. By doing so, our relevance estimation can be proved to be free of bias. To implement InfoRank, we first incorporate an attention mechanism to capture latent correlations within user-item features, thereby generating estimations of observation and relevance. We then introduce a regularization term, grounded in conditional mutual information, to promote conditional independence between relevance estimation and observation estimation. Experimental evaluations conducted across three extensive recommendation and search datasets reveal that InfoRank learns more precise and unbiased ranking strategies.
Supplemental Material
- Himan Abdollahpouri, Robin Burke, and Bamshad Mobasher. 2017. Controlling popularity bias in learning-to-rank recommendation. In RecSys.Google Scholar
- Aman Agarwal, Kenta Takatsu, Ivan Zaitsev, and Thorsten Joachims. 2019. A general framework for counterfactual learning-to-rank. In SIGIR.Google Scholar
- Aman Agarwal, Ivan Zaitsev, Xuanhui Wang, Cheng Li, Marc Najork, and Thorsten Joachims. 2019. Estimating position bias without intrusive interventions. In WSDM.Google Scholar
- Qingyao Ai, Keping Bi, Cheng Luo, Jiafeng Guo, and W Bruce Croft. 2018. Unbiased learning to rank with unbiased propensity estimation. In SIGIR.Google Scholar
- Qingyao Ai, Jiaxin Mao, Yiqun Liu, and W Bruce Croft. 2018. Unbiased learning to rank: Theory and practice. In CIKM.Google Scholar
- Christopher JC Burges. 2010. From ranknet to lambdarank to lambdamart: An overview. Learning (2010).Google Scholar
- Abhijnan Chakraborty, Gourab K Patro, Niloy Ganguly, Krishna P Gummadi, and Patrick Loiseau. 2019. Equality of voice: Towards fair representation in crowdsourced top-k recommendations. In Proceedings of the Conference on Fairness, Accountability, and Transparency.Google ScholarDigital Library
- Olivier Chapelle and Yi Chang. 2011. Yahoo! learning to rank challenge overview. In Proceedings of the learning to rank challenge.Google ScholarDigital Library
- Olivier Chapelle and Ya Zhang. 2009. A dynamic bayesian network click model for web search ranking. In WWW.Google Scholar
- Jiawei Chen, Hande Dong, FengWang, Xiang,Wang Fuli, He Meng, and Xiangnan. 2020. Bias and Debias in Recommender System: A Survey and Future Directions. arXiv preprint (2020).Google Scholar
- 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 DLRS.Google Scholar
- Konstantina Christakopoulou, Madeleine Traverse, Trevor Potter, Emma Marriott, Daniel Li, Chris Haulk, Ed H Chi, and Minmin Chen. 2020. Deconfounding user satisfaction estimation from response rate bias. In Proceedings of the 14th ACM Conference on Recommender Systems. 450--455.Google ScholarDigital Library
- Paul Covington, Jay Adams, and Emre Sargin. 2016. Deep neural networks for youtube recommendations. In RecSys.Google Scholar
- Nick Craswell, Onno Zoeter, Michael Taylor, and Bill Ramsey. 2008. An experimental comparison of click position-bias models. In WSDM.Google Scholar
- Georges E Dupret and Benjamin Piwowarski. 2008. A user browsing model to predict search engine click data from past observations.. In SIGIR.Google Scholar
- Michael D Ekstrand, Mucun Tian, Ion Madrazo Azpiazu, Jennifer D Ekstrand, Oghenemaro Anuyah, David McNeill, and Maria Soledad Pera. 2018. All the cool kids, how do they fit in?: Popularity and demographic biases in recommender evaluation and effectiveness. In Conference on Fairness, Accountability and Transparency.Google Scholar
- Zhichong Fang, Aman Agarwal, and Thorsten Joachims. 2019. Intervention harvesting for context-dependent examination-bias estimation. In SIGIR.Google Scholar
- Jon Atle Gulla, Lemei Zhang, Peng Liu, Özlem Özgöbek, and Xiaomeng Su. 2017. The Adressa dataset for news recommendation. In Proceedings of the international conference on web intelligence.Google ScholarDigital Library
- Fan Guo, Chao Liu, Anitha Kannan, Tom Minka, Michael Taylor, Yi-Min Wang, and Christos Faloutsos. 2009. Click chain model in web search. In WWW.Google Scholar
- Priyanka Gupta, Ankit Sharma, Pankaj Malhotra, Lovekesh Vig, and Gautam Shroff. 2021. Causer: Causal session-based recommendations for handling popularity bias. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 3048--3052.Google ScholarDigital Library
- Katja Hofmann, Anne Schuth, Alejandro Bellogin, and Maarten De Rijke. 2014. Effects of position bias on click-based recommender evaluation. In ECIR.Google Scholar
- Ziniu Hu, Yang Wang, Qu Peng, and Hang Li. 2019. Unbiased LambdaMART: An unbiased pairwise learning-to-rank algorithm. In WWW.Google Scholar
- Rolf Jagerman, Harrie Oosterhuis, and Maarten de Rijke. 2019. To model or to intervene: A comparison of counterfactual and online learning to rank from user interactions. In SIGIR.Google Scholar
- Jiarui Jin, Yuchen Fang, Weinan Zhang, Kan Ren, Guorui Zhou, Jian Xu, Yong Yu, Jun Wang, Xiaoqiang Zhu, and Kun Gai. 2020. A Deep Recurrent Survival Model for Unbiased Ranking. In SIGIR.Google Scholar
- Thorsten Joachims, Laura Granka, Bing Pan, Helene Hembrooke, and Geri Gay. 2017. Accurately interpreting clickthrough data as implicit feedback. In SIGIR.Google Scholar
- Thorsten Joachims, Laura A Granka, Bing Pan, Helene Hembrooke, and Geri Gay. 2005. Accurately interpreting clickthrough data as implicit feedback. In SIGIR.Google Scholar
- Thorsten Joachims, Adith Swaminathan, and Tobias Schnabel. 2017. Unbiased learning-to-rank with biased feedback. In WSDM.Google Scholar
- Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, and Jun Sakuma. 2014. Correcting Popularity Bias by Enhancing Recommendation Neutrality.. In RecSys Posters.Google Scholar
- Adit Krishnan, Ashish Sharma, Aravind Sankar, and Hari Sundaram. 2018. An adversarial approach to improve long-tail performance in neural collaborative filtering. In CIKM.Google Scholar
- Dan Luo, Lixin Zou, Qingyao Ai, Zhiyu Chen, Chenliang Li, Dawei Yin, and Brian D Davison. 2023. Unconfounded Propensity Estimation for Unbiased Ranking. arXiv preprint arXiv:2305.09918 (2023).Google Scholar
- Harrie Oosterhuis and Maarten de Rijke. 2021. Unifying Online and Counterfactual Learning to Rank: A Novel Counterfactual Estimator that Effectively Utilizes Online Interventions. In WSDM.Google Scholar
- Judea Pearl et al. 2000. Models, reasoning and inference. Cambridge, UK: CambridgeUniversityPress 19, 2 (2000), 3.Google Scholar
- Tao Qin, Tie-Yan Liu, Jun Xu, and Hang Li. 2010. LETOR: A benchmark collection for research on learning to rank for information retrieval. Information Retrieval (2010).Google Scholar
- Yanru Qu, Han Cai, Kan Ren, Weinan Zhang, Yong Yu, Ying Wen, and Jun Wang. 2016. Product-based neural networks for user response prediction. In ICDM.Google Scholar
- Steffen Rendle. 2010. Factorization machines. In ICDM.Google Scholar
- Matthew Richardson, Ewa Dominowska, and Robert Ragno. 2007. Predicting clicks: estimating the click-through rate for new ads. In WWW.Google Scholar
- Paul R Rosenbaum and Donald B Rubin. 1983. The central role of the propensity score in observational studies for causal effects. Biometrika (1983).Google Scholar
- Masahiro Sato, Sho Takemori, Janmajay Singh, and Tomoko Ohkuma. 2020. Unbiased learning for the causal effect of recommendation. In Proceedings of the 14th ACM Conference on Recommender Systems. 378--387.Google ScholarDigital Library
- Ying Shan, T Ryan Hoens, Jian Jiao, Haijing Wang, Dong Yu, and JC Mao. 2016. Deep crossing: Web-scale modeling without manually crafted combinatorial features. In KDD.Google Scholar
- Xiaoyuan Su and Taghi M Khoshgoftaar. 2009. A survey of collaborative filtering techniques. Advances in artificial intelligence 2009 (2009).Google Scholar
- Anh Tran, Tao Yang, and Qingyao Ai. 2021. ULTRA: An Unbiased Learning To Rank Algorithm Toolbox. In CIKM.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS.Google Scholar
- Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. ICLR (2018).Google Scholar
- Chao Wang, Yiqun Liu, Meng Wang, Ke Zhou, Jian-yun Nie, and Shaoping Ma. 2015. Incorporating non-sequential behavior into click models. In SIGIR.Google Scholar
- Hongning Wang, ChengXiang Zhai, Anlei Dong, and Yi Chang. 2013. Contentaware click modeling. In WWW.Google Scholar
- JunWang, Arjen P De Vries, and Marcel JT Reinders. 2006. A user-item relevance model for log-based collaborative filtering. In ECIR.Google Scholar
- Nan Wang, Xuanhui Wang, and Hongning Wang. 2020. Unbiased Learning to Rank via Propensity Ratio Scoring. In SIGIR.Google Scholar
- Wenjie Wang, Fuli Feng, Xiangnan He, Xiang Wang, and Tat-Seng Chua. 2021. Deconfounded recommendation for alleviating bias amplification. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1717--1725.Google ScholarDigital Library
- Xuanhui Wang, Michael Bendersky, Donald Metzler, and Marc Najork. 2016. Learning to rank with selection bias in personal search. In SIGIR.Google Scholar
- Xuanhui Wang, Nadav Golbandi, Michael Bendersky, Donald Metzler, and Marc Najork. 2018. Position bias estimation for unbiased learning to rank in personal search. In WSDM.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.Google Scholar
- Le Yan, Zhen Qin, Honglei Zhuang, Xuanhui Wang, Mike Bendersky, and Marc Najork. 2022. Revisiting two tower models for unbiased learning to rank. (2022).Google Scholar
- Xing Yi, Liangjie Hong, Erheng Zhong, Nanthan Nan Liu, and Suju Rajan. 2014. Beyond clicks: dwell time for personalization. In RecSys.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 Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 11--20.Google ScholarDigital Library
- Zhe Zhao, Lichan Hong, Li Wei, Jilin Chen, Aniruddh Nath, Shawn Andrews, Aditee Kumthekar, Maheswaran Sathiamoorthy, Xinyang Yi, and Ed Chi. 2019. Recommending what video to watch next: a multitask ranking system. In RecSys.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 KDD.Google Scholar
- Ziwei Zhu, Yun He, Xing Zhao, and James Caverlee. 2021. Popularity Bias in Dynamic Recommendation. (2021).Google Scholar
Index Terms
- InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization
Recommendations
Unbiased LambdaMART: An Unbiased Pairwise Learning-to-Rank Algorithm
WWW '19: The World Wide Web ConferenceRecently a number of algorithms under the theme of 'unbiased learning-to-rank' have been proposed, which can reduce position bias, the major type of bias in click data, and train a high-performance ranker with click data. Most of the existing algorithms,...
A General Framework for Pairwise Unbiased Learning to Rank
ICTIR '22: Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information RetrievalPairwise debiasing is one of the most effective strategies in reducing position bias in learning-to-rank (LTR) models. However, limiting the scope of this strategy, are the underlying assumptions required by many pairwise debiasing approaches. In this ...
Unbiased Learning to Rank with Biased Continuous Feedback
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementIt is a well-known challenge to learn an unbiased ranker with biased feedback. Unbiased learning-to-rank(LTR) algorithms, which are verified to model the relative relevance accurately based on noisy feedback, are appealing candidates and have already ...
Comments