Taking Advantage of the Mistakes: Rethinking Clustered Federated Learning for IoT Anomaly Detection
Jiamin Fan, Kui Wu, Guoming Tang, Yang Zhou, Shengqiang Huang
Abstract
Clustered federated learning (CFL) is a promising solution to address the non-IID problem in the spatial domain for federated learning (FL). However, existing CFL solutions overlook the non-IID issue in the temporal domain and lack consideration of time efficiency. In this work, we propose a novel approach, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ClusterFLADS</i> , which takes advantage of the false predictions of the inappropriate global models, together with knowledge of temperature scaling and catastrophic forgetting to reveal distributional similarities between the training data (of different clusters) and the test data. Additionally, we design an efficient feature extraction scheme by exploiting the role of each layer in a neural network's learning process. By strategically selecting model parameters and using PCA for dimensionality reduction, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ClusterFLADS</i> effectively improves clustering speed. We evaluate <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ClusterFLADS</i> using real-world IoT trace data in various scenarios. Our results show that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ClusterFLADS</i> accurately and efficiently clusters clients, achieving a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$100\%$</tex-math></inline-formula> true positive rate and low false positives across various data distributions in both the spatial and temporal domains.