TY - GEN N1 - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions. SP - 1350 A1 - Jin, J A1 - He, Z A1 - Yang, M A1 - Zhang, W A1 - Yu, Y A1 - Wang, J A1 - McAuley, J PB - Association for Computing Machinery (ACM) Y1 - 2024/05/13/ CY - Singapore, Singapore TI - InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization AV - public N2 - 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. ID - discovery10194856 UR - http://dx.doi.org/10.1145/3589334.3645356 EP - 1361 ER -