User Fairness in Recommender Systems

Abstract

Recent works in recommendation systems have focused on diversity in recommendations as an important aspect of recommendation quality. In this work we argue that the post-processing algorithms aimed at only improving diversity among recommendations lead to discrimination among the users. We introduce the notion of user fairness which has been overlooked in literature so far and propose measures to quantify it. Our experiments on two diversification algorithms show that an increase in aggregate diversity results in increased disparity among the users.

Cited by in corpus (8)

• Building Human Values into Recommender Systems: An Interdisciplinary Synthesis
• Deep Learning feature selection to unhide demographic recommender systems factors
• DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias
• Uncovering Bias in Personal Informatics
• Stairway to Fairness: Connecting Group and Individual Fairness
• Mitigating Mainstream Bias in Recommendation via Cost-sensitive Learning
• Guaranteeing Accuracy and Fairness under Fluctuating User Traffic: A Bankruptcy-Inspired Re-ranking Approach
• Evaluating and Addressing Fairness Across User Groups in Negative Sampling for Recommender Systems