Federated Gaussian Mixture Models

TL;DR

FedGenGMM introduces a one-shot federated learning method for Gaussian Mixture Models that reduces communication costs and handles data heterogeneity effectively, suitable for edge computing.

Contribution

It presents a novel one-shot federated GMM approach that creates a synthetic dataset for efficient global model training without multiple communication rounds.

Findings

Achieves comparable performance to iterative methods

Reduces communication overhead significantly

Maintains robustness in anomaly detection

Abstract

This paper introduces FedGenGMM, a novel one-shot federated learning approach for Gaussian Mixture Models (GMM) tailored for unsupervised learning scenarios. In federated learning (FL), where multiple decentralized clients collaboratively train models without sharing raw data, significant challenges include statistical heterogeneity, high communication costs, and privacy concerns. FedGenGMM addresses these issues by allowing local GMM models, trained independently on client devices, to be aggregated through a single communication round. This approach leverages the generative property of GMMs, enabling the creation of a synthetic dataset on the server side to train a global model efficiently. Evaluation across diverse datasets covering image, tabular, and time series data demonstrates that FedGenGMM consistently achieves performance comparable to non-federated and iterative federated methods, even under significant data heterogeneity. Additionally, FedGenGMM significantly reduces communication overhead, maintains robust performance in anomaly detection tasks, and offers flexibility in local model complexities, making it particularly suitable for edge computing environments.