The Impact of Differential Privacy on Recommendation Accuracy and Popularity Bias

TL;DR

This paper investigates how applying Differential Privacy to recommender systems affects their accuracy and popularity bias, revealing significant impacts on user recommendations and increased bias, especially for users favoring unpopular items.

Contribution

It provides a comprehensive analysis of the effects of Differential Privacy on recommendation accuracy and popularity bias, highlighting the exacerbation of bias for certain user groups.

Findings

Recommendation changes for nearly all users with DP

Substantial drop in recommendation accuracy due to DP

Popularity bias increases sharply, especially for users preferring unpopular items

Abstract

Collaborative filtering-based recommender systems leverage vast amounts of behavioral user data, which poses severe privacy risks. Thus, often, random noise is added to the data to ensure Differential Privacy (DP). However, to date, it is not well understood, in which ways this impacts personalized recommendations. In this work, we study how DP impacts recommendation accuracy and popularity bias, when applied to the training data of state-of-the-art recommendation models. Our findings are three-fold: First, we find that nearly all users' recommendations change when DP is applied. Second, recommendation accuracy drops substantially while recommended item popularity experiences a sharp increase, suggesting that popularity bias worsens. Third, we find that DP exacerbates popularity bias more severely for users who prefer unpopular items than for users that prefer popular items.