Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networks

TL;DR

This paper proposes a federated learning framework with adaptive model pruning and personalization, reducing latency and improving accuracy on heterogeneous devices over wireless networks.

Contribution

It introduces a novel FL framework that splits models into global and personalized parts, optimizing pruning and bandwidth to enhance performance and efficiency.

Findings

Reduces computation and communication latency by ~50%.

Improves learning accuracy on non-i.i.d. data.

Provides mathematical analysis of latency and convergence.

Abstract

Federated learning (FL) enables distributed learning across edge devices while protecting data privacy. However, the learning accuracy decreases due to the heterogeneity of devices' data, and the computation and communication latency increase when updating large-scale learning models on devices with limited computational capability and wireless resources. We consider a FL framework with partial model pruning and personalization to overcome these challenges. This framework splits the learning model into a global part with model pruning shared with all devices to learn data representations and a personalized part to be fine-tuned for a specific device, which adapts the model size during FL to reduce both computation and communication latency and increases the learning accuracy for devices with non-independent and identically distributed data. The computation and communication latency and convergence of the proposed FL framework are mathematically analyzed. To maximize the convergence rate and guarantee learning accuracy, Karush Kuhn Tucker (KKT) conditions are deployed to jointly optimize the pruning ratio and bandwidth allocation. Finally, experimental results demonstrate that the proposed FL framework achieves a remarkable reduction of approximately 50 percent computation and communication latency compared with FL with partial model personalization.