DeepAI AI Chat
Log In Sign Up

Differentially Private Federated Clustering over Non-IID Data

by   Yiwei Li, et al.

Federated clustering (FedC) is an adaptation of centralized clustering in federated settings, which aims to cluster data based on a global similarity measure while keeping all data locally. Two of the main challenges of FedC are the non-identically and independently distributed (non-i.i.d.) nature of data across different sources, as well as the need for privacy protection. In this paper, we propose a differentially private federated clustering (DP-FedC) algorithm to deal with these challenges. Unlike most existing algorithms without considering privacy, the proposed DP-FedC algorithm is designed to handle non-convex and non-smooth problems by using differential privacy techniques to guarantee privacy, together with privacy amplification assisted tradeoff between learning performance and privacy protection. Then some theoretical analyses of the performance and privacy of the proposed DP-FedC are presented, showing the impact of privacy protection, data heterogeneity, and partial client participation on learning performance. Finally, some experimental results are presented to demonstrate the efficacy (including analytical results) of the proposed DP-FedC algorithm together with its superior performance over state-of-the-art approaches.


page 1

page 2

page 3

page 4


DP-REC: Private Communication-Efficient Federated Learning

Privacy and communication efficiency are important challenges in federat...

Differentially Private Federated Bayesian Optimization with Distributed Exploration

Bayesian optimization (BO) has recently been extended to the federated l...

Differentially Private Federated Learning via Inexact ADMM

Differential privacy (DP) techniques can be applied to the federated lea...

A Theoretical Perspective on Differentially Private Federated Multi-task Learning

In the era of big data, the need to expand the amount of data through da...

DPSNN: A Differentially Private Spiking Neural Network

Privacy-preserving is a key problem for the machine learning algorithm. ...

DPOAD: Differentially Private Outsourcing of Anomaly Detection through Iterative Sensitivity Learning

Outsourcing anomaly detection to third-parties can allow data owners to ...

Differentially-private Federated Neural Architecture Search

Neural architecture search, which aims to automatically search for archi...