Near-Optimal Correlation Clustering with PrivacyDownload PDF

Published: 31 Oct 2022, Last Modified: 13 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: Clustering, Correlation Clustering, Differential Privacy, Approximation Algorithms
Abstract: Correlation clustering is a central problem in unsupervised learning, with applications spanning community detection, duplicate detection, automated labeling and many more. In the correlation clustering problem one receives as input a set of nodes and for each node a list of co-clustering preferences, and the goal is to output a clustering that minimizes the disagreement with the specified nodes' preferences. In this paper, we introduce a simple and computationally efficient algorithm for the correlation clustering problem with provable privacy guarantees. Our additive error is stronger than those obtained in prior work and is optimal up to polylogarithmic factors for fixed privacy parameters.
TL;DR: We propose an improved differentially private algorithm with constant approximation guarantee for the correlation clustering problem.
Supplementary Material: pdf
13 Replies