Redefining Clustered Federated Learning for System Identification: The Path of ClusterCraft

TL;DR

This paper presents IC-SYSID, a novel federated learning algorithm for system identification that dynamically clusters data sources without prior knowledge, improving stability and performance in real-world vehicle dynamics applications.

Contribution

The paper introduces ClusterCraft, an incremental clustering method integrated into federated learning for SYSID, eliminating the need for prior dataset knowledge and enhancing model stability.

Findings

IC-SYSID achieves high SYSID performance on real-world vehicle data.

The method effectively prevents unstable cluster learning.

Enhanced clustering reduces model redundancy.

Abstract

This paper addresses the System Identification (SYSID) problem within the framework of federated learning. We introduce a novel algorithm, Incremental Clustering-based federated learning method for SYSID (IC-SYSID), designed to tackle SYSID challenges across multiple data sources without prior knowledge. IC-SYSID utilizes an incremental clustering method, ClusterCraft (CC), to eliminate the dependency on the prior knowledge of the dataset. CC starts with a single cluster model and assigns similar local workers to the same clusters by dynamically increasing the number of clusters. To reduce the number of clusters generated by CC, we introduce ClusterMerge, where similar cluster models are merged. We also introduce enhanced ClusterCraft to reduce the generation of similar cluster models during the training. Moreover, IC-SYSID addresses cluster model instability by integrating a regularization term into the loss function and initializing cluster models with scaled Glorot initialization. It also utilizes a mini-batch deep learning approach to manage large SYSID datasets during local training. Through the experiments conducted on a real-world representing SYSID problem, where a fleet of vehicles collaboratively learns vehicle dynamics, we show that IC-SYSID achieves a high SYSID performance while preventing the learning of unstable clusters.