Federated Structured Sparse PCA for Anomaly Detection in IoT Networks
Chenyi Huang, Xianchao Xiu
TL;DR
This work addresses privacy-preserving anomaly detection in IoT by augmenting federated PCA with double sparsity. It introduces a FedSSP model that enforces row-wise sparsity via $\|W\|_{2,p}^{p}$ and element-wise sparsity via $\|W\|_{q}^{q}$, with $p,q\in[0,1)$, and solves the nonconvex problem using proximal alternating minimization on a Grassmann manifold. The method introduces a global variable $Z$ and auxiliary variables $U_t$, $V_t$, achieving efficient distributed optimization and improved interpretability and detection performance on the TON dataset, compared to FedPG and FedAE. The results suggest that double sparsity enhances both reconstruction-based anomaly detection and local discrimination, with code available for replication.
Abstract
Although federated learning has gained prominence as a privacy-preserving framework tailored for distributed Internet of Things (IoT) environments, current federated principal component analysis (PCA) methods lack integration of sparsity, a critical feature for robust anomaly detection. To address this limitation, we propose a novel federated structured sparse PCA (FedSSP) approach for anomaly detection in IoT networks. The proposed model uniquely integrates double sparsity regularization: (1) row-wise sparsity governed by $\ell_{2,p}$-norm with $p\in [0,1)$ to eliminate redundant feature dimensions, and (2) element-wise sparsity via $\ell_{q}$-norm with $q\in [0,1)$ to suppress noise-sensitive components. To solve this nonconvex problem in a distributed setting, we devise an efficient optimization algorithm based on the proximal alternating minimization (PAM). Numerical experiments validate that incorporating structured sparsity enhances both model interpretability and detection accuracy. Our code is available at https://github.com/xianchaoxiu/FedSSP.