Cuize Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Cuize Han has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Parth Gupta
Amazon, Palo Alto, CA, USA
2 shared publications - Chen Luo
Amazon Search, Palo Alto, CA, USA
1 shared publication - Jeff M. Phillips
University of Utah
1 shared publication - Paul Musgrave
Amazon Search, Palo Alto, CA, USA
1 shared publication - Qingyao Ai
Tsinghua University, Beijing, China
1 shared publication - Tao Yang
University of Utah, Salt Lake City, UT, USA
1 shared publication
Latest Publications
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1486-1496
Mitigating Exploitation Bias in Learning to Rank with an Uncertainty-aware Empirical Bayes Approach
Ranking is at the core of many artificial intelligence (AI) applications, including search engines, recommender systems, etc. Modern ranking systems are often constructed with learning-to-rank (LTR) models built from user behavior signals. While previous studies have demonstrated the effectiveness of using user behavior signals (e.g., clicks) as both features and labels of LTR algorithms, we argue that existing LTR algorithms that indiscriminately treat behavior and non-behavior signals in input features could lead to suboptimal performance in practice. Because user behavior signals often have strong correlations with the ranking objective and can only be collected on items that have already been shown to users, directly using behavior signals in LTR could create an exploitation bias that hurts the system performance in the long run. To address the exploitation bias, we propose an uncertainty-aware empirical Bayes based ranking algorithm, referred to as EBRank. Specifically, EBRank uses a sole non-behavior feature-based prior model to get a prior estimation of relevance. In the dynamic training and serving of ranking systems, EBRank uses the observed user behaviors to update posterior relevance estimation instead of concatenating behaviors as features in ranking models. Besides, EBRank additionally applies an uncertainty-aware exploration strategy to explore actively and collect user behaviors for empirical Bayesian modeling. Experiments on three public datasets show that EBRank is effective, practical and significantly outperforms state-of-the-art ranking algorithms.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1486-1496
Open AccessMitigating Exploitation Bias in Learning to Rank with an Uncertainty-aware Empirical Bayes Approach
Ranking is at the core of many artificial intelligence (AI) applications, including search engines, recommender systems, etc. Modern ranking systems are often constructed with learning-to-rank (LTR) models built from user behavior signals. While previous studies have demonstrated the effectiveness of using user behavior signals (e.g., clicks) as both features and labels of LTR algorithms, we argue that existing LTR algorithms that indiscriminately treat behavior and non-behavior signals in input features could lead to suboptimal performance in practice. Because user behavior signals often have strong correlations with the ranking objective and can only be collected on items that have already been shown to users, directly using behavior signals in LTR could create an exploitation bias that hurts the system performance in the long run. To address the exploitation bias, we propose an uncertainty-aware empirical Bayes based ranking algorithm, referred to as EBRank. Specifically, EBRank uses a sole non-behavior feature-based prior model to get a prior estimation of relevance. In the dynamic training and serving of ranking systems, EBRank uses the observed user behaviors to update posterior relevance estimation instead of concatenating behaviors as features in ranking models. Besides, EBRank additionally applies an uncertainty-aware exploration strategy to explore actively and collect user behaviors for empirical Bayesian modeling. Experiments on three public datasets show that EBRank is effective, practical and significantly outperforms state-of-the-art ranking algorithms.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2169-2173
Measuring Service-Level Learning Effects in Search Via Query-Randomized Experiments
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2169-2173
Open AccessMeasuring Service-Level Learning Effects in Search Via Query-Randomized Experiments