Naturally Private Recommendations with Determinantal Point Processes

Authors: Jack Fitzsimons, Agustín Freitas Pasqualini, Robert Pisarczyk, Dmitrii Usynin
Published: 2024-05-22

Source: https://arxiv.org/abs/2405.13677

PDF: https://arxiv.org/pdf/2405.13677

Labels Predicted by AI

ウォーターマーキング プライバシー保護手法 透かし評価

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Often we consider machine learning models or statistical analysis methods which we endeavour to alter, by introducing a randomized mechanism, to make the model conform to a differential privacy constraint. However, certain models can often be implicitly differentially private or require significantly fewer alterations. In this work, we discuss Determinantal Point Processes (DPPs) which are dispersion models that balance recommendations based on both the popularity and the diversity of the content. We introduce DPPs, derive and discuss the alternations required for them to satisfy epsilon-Differential Privacy and provide an analysis of their sensitivity. We conclude by proposing simple alternatives to DPPs which would make them more efficient with respect to their privacy-utility trade-off.