An Efficient Unsupervised Federated Learning Approach for Anomaly Detection in Heterogeneous IoT Networks

2026-02-27

AI Summary

This work proposes an efficient unsupervised federated learning framework to address the performance degradation and feature heterogeneity in anomaly detection caused by diverse device capabilities, data formats, and communication constraints in heterogeneous IoT environments. By introducing a feature disentanglement mechanism, the approach jointly leverages shared representations from two complementary tasks— anomaly detection and device identification—while preserving their task-specific features, thereby enhancing model generalization. Furthermore, interpretable AI techniques such as SHAP are integrated to improve decision transparency. As the first study to exploit cross-task complementary datasets for optimizing unsupervised federated learning, the proposed method substantially mitigates feature inconsistency and achieves significantly higher anomaly detection accuracy than existing federated learning approaches on real-world IoT datasets.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Federated learning (FL) is an effective paradigm for distributed environments such as the Internet of Things (IoT), where data from diverse devices with varying functionalities remains localized while contributing to a shared global model. By eliminating the need to transmit raw data, FL inherently preserves privacy. However, the heterogeneous nature of IoT data, stemming from differences in device capabilities, data formats, and communication constraints, poses significant challenges to maintaining both global model performance and privacy. In the context of IoT-based anomaly detection, unsupervised FL offers a promising means to identify abnormal behavior without centralized data aggregation. Nevertheless, feature heterogeneity across devices complicates model training and optimization, hindering effective implementation. In this study we propose an efficient unsupervised FL framework that enhances anomaly detection by leveraging shared features from two distinct IoT datasets: one focused on anomaly detection and the other on device identification, while preserving dataset-specific features. To improve transparency and interpretability, we employ explainable AI techniques, such as SHAP, to identify key features influencing local model decisions. Experiments conducted on real-world IoT datasets demonstrate that the proposed method significantly outperforms conventional FL approaches in anomaly detection accuracy. This work underscores the potential of using shared features from complementary datasets to optimize unsupervised federated learning and achieve superior anomaly detection results in decentralized IoT environments.

Problem

• Federated Learning
• Anomaly Detection
• Heterogeneous IoT Networks
• Unsupervised Learning
• Feature Heterogeneity

Innovation

• Unsupervised Federated Learning
• Feature Heterogeneity
• Shared Feature Representation
• Explainable AI (XAI)
• IoT Anomaly Detection