Poster
in
Workshop: Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities

Differentially Private Heavy Hitters using Federated Analytics

Karan Chadha ⋅ Junye Chen ⋅ John Duchi ⋅ Vitaly Feldman ⋅ Hanieh Hashemi ⋅ Omid Javidbakht ⋅ Audra McMillan ⋅ Kunal Talwar

Project Page [ OpenReview]

Abstract

We study practical heuristics to improve the performance of prefix-tree based algorithms for differentially private heavy hitter detection. Our model assumes each user has multiple data points and the goal is to learn as many of the most frequent data points as possible across all users' data with aggregate and local differential privacy.

Chat is not available.