FedPURIN: Programmed Update and Reduced INformation for Sparse Personalized Federated Learning
This addresses communication burdens in edge intelligence systems with heterogeneous data, though it is incremental as it builds on existing parameter decoupling paradigms.
The paper tackles communication inefficiency in personalized federated learning by proposing FedPURIN, a framework that uses integer programming to identify critical parameters for transmission, achieving significant communication reduction while maintaining competitive performance on image classification benchmarks under non-IID conditions.
Personalized Federated Learning (PFL) has emerged as a critical research frontier addressing data heterogeneity issue across distributed clients. Novel model architectures and collaboration mechanisms are engineered to accommodate statistical disparities while producing client-specific models. Parameter decoupling represents a promising paradigm for maintaining model performance in PFL frameworks. However, the communication efficiency of many existing methods remains suboptimal, sustaining substantial communication burdens that impede practical deployment. To bridge this gap, we propose Federated Learning with Programmed Update and Reduced INformation (FedPURIN), a novel framework that strategically identifies critical parameters for transmission through an integer programming formulation. This mathematically grounded strategy is seamlessly integrated into a sparse aggregation scheme, achieving a significant communication reduction while preserving the efficacy. Comprehensive evaluations on standard image classification benchmarks under varied non-IID conditions demonstrate competitive performance relative to state-of-the-art methods, coupled with quantifiable communication reduction through sparse aggregation. The framework establishes a new paradigm for communication-efficient PFL, particularly advantageous for edge intelligence systems operating with heterogeneous data sources.