Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices

TL;DR

This paper introduces FedMPQ, a federated learning algorithm that employs mixed-precision quantization to reduce communication costs on heterogeneous devices, achieving better performance than fixed-precision methods with minimal overhead.

Contribution

The paper proposes a novel federated learning algorithm, FedMPQ, that applies mixed-precision quantization with adaptive bit-width assignment to improve efficiency on resource-heterogeneous devices.

Findings

FedMPQ outperforms fixed-precision schemes in various benchmarks.

The method incurs only minor computational overhead.

Effective in both iid and non-iid data settings.

Abstract

While federated learning (FL) systems often utilize quantization to battle communication and computational bottlenecks, they have heretofore been limited to deploying fixed-precision quantization schemes. Meanwhile, the concept of mixed-precision quantization (MPQ), where different layers of a deep learning model are assigned varying bit-width, remains unexplored in the FL settings. We present a novel FL algorithm, FedMPQ, which introduces mixed-precision quantization to resource-heterogeneous FL systems. Specifically, local models, quantized so as to satisfy bit-width constraint, are trained by optimizing an objective function that includes a regularization term which promotes reduction of precision in some of the layers without significant performance degradation. The server collects local model updates, de-quantizes them into full-precision models, and then aggregates them into a global model. To initialize the next round of local training, the server relies on the information learned in the previous training round to customize bit-width assignments of the models delivered to different clients. In extensive benchmarking experiments on several model architectures and different datasets in both iid and non-iid settings, FedMPQ outperformed the baseline FL schemes that utilize fixed-precision quantization while incurring only a minor computational overhead on the participating devices.