Model Pruning Enables Efficient Federated Learning on Edge Devices

TL;DR

PruneFL is a novel federated learning method that adaptively prunes models during training on edge devices, significantly reducing training time while maintaining accuracy comparable to the original model.

Contribution

The paper introduces PruneFL, an adaptive distributed pruning approach that reduces communication and computation in federated learning on resource-constrained edge devices.

Findings

Significantly reduces training time compared to traditional FL.

Maintains model accuracy similar to the original model after pruning.

Pruned models serve as lottery tickets, preserving essential performance.

Abstract

Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision applications. A challenge is that client devices in FL usually have much more limited computation and communication resources compared to servers in a datacenter. To overcome this challenge, we propose PruneFL -- a novel FL approach with adaptive and distributed parameter pruning, which adapts the model size during FL to reduce both communication and computation overhead and minimize the overall training time, while maintaining a similar accuracy as the original model. PruneFL includes initial pruning at a selected client and further pruning as part of the FL process. The model size is adapted during this process, which includes maximizing the approximate empirical risk reduction divided by the time of one FL round. Our experiments with various datasets on edge devices (e.g., Raspberry Pi) show that: (i) we significantly reduce the training time compared to conventional FL and various other pruning-based methods; (ii) the pruned model with automatically determined size converges to an accuracy that is very similar to the original model, and it is also a lottery ticket of the original model.