Fair Recommendations with Limited Sensitive Attributes - A Distributionally Robust Optimization Approach

Fair Recommendations with Limited Sensitive Attributes - A Distributionally Robust Optimization Approach

Explore a conference talk on fair recommendations in recommender systems with limited sensitive attributes. Delve into a distributionally robust optimization approach presented by authors Tianhao Shi, Yang Zhang, Jizhi Zhang, Fuli Feng, and Xiangnan He. Learn about innovative techniques to address fairness challenges in recommendation algorithms when dealing with limited access to sensitive user information. Gain insights into the intersection of fairness, privacy, and machine learning in the context of recommender systems during this 14-minute presentation from the Association for Computing Machinery (ACM) SIGIR 2024 conference.