Efficient Personalized Federated PCA with Manifold Optimization for IoT Anomaly Detection

TL;DR

This paper introduces FedEP, a novel personalized federated PCA method with manifold optimization, enhancing IoT anomaly detection by integrating personalization and robustness, and demonstrating superior performance over existing methods.

Contribution

The paper proposes FedEP, a personalized federated PCA approach using manifold optimization and sparsity norms, addressing limitations of prior federated PCA methods for IoT security.

Findings

FedEP outperforms state-of-the-art FedPG in F1-score and accuracy.

The method demonstrates effective anomaly detection in various IoT security scenarios.

Theoretical convergence guarantees are established for the optimization algorithm.

Abstract

Internet of things (IoT) networks face increasing security threats due to their distributed nature and resource constraints. Although federated learning (FL) has gained prominence as a privacy-preserving framework for distributed IoT environments, current federated principal component analysis (PCA) methods lack the integration of personalization and robustness, which are critical for effective anomaly detection. To address these limitations, we propose an efficient personalized federated PCA (FedEP) method for anomaly detection in IoT networks. The proposed model achieves personalization through introducing local representations with the $\ell_1$-norm for element-wise sparsity, while maintaining robustness via enforcing local models with the $\ell_{2,1}$-norm for row-wise sparsity. To solve this non-convex problem, we develop a manifold optimization algorithm based on the alternating direction method of multipliers (ADMM) with rigorous theoretical convergence guarantees. Experimental results confirm that the proposed FedEP outperforms the state-of-the-art FedPG, achieving excellent F1-scores and accuracy in various IoT security scenarios. Our code will be available at \href{https://github.com/xianchaoxiu/FedEP}{https://github.com/xianchaoxiu/FedEP}.