Formal Logic Enabled Personalized Federated Learning through Property Inference

Abstract

Recent advancements in federated learning (FL) have greatly facilitated the development of decentralized collaborative applications, particularly in the domain of Artificial Intelligence of Things (AIoT). However, a critical aspect missing from the current research landscape is the ability to enable data-driven client models with symbolic reasoning capabilities. Specifically, the inherent heterogeneity of participating client devices poses a significant challenge, as each client exhibits unique logical reasoning properties. Failing to consider these device-specific specifications can result in missing critical properties in the client predictions, leading to suboptimal performance. This work proposes a new training paradigm that leverages temporal logic reasoning to address this issue. Our approach enhances the training process by incorporating mechanically generated logic expressions for each FL client. Additionally, we develop aggregation clusters and a partitioning algorithm to effectively group clients based on the alignment of their temporal reasoning properties. We evaluate the proposed method on two tasks: a real-world traffic volume prediction task consisting of sensory data from fifteen states and a smart city multi-task prediction utilizing synthetic data. The evaluation results exhibit clear improvements, with performance accuracy improved by up to 54% across all sequential prediction models.