English

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

Machine Learning 2023-12-01 v1 Distributed, Parallel, and Cluster Computing

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.

Keywords

Cite

@article{arxiv.2311.18129,
  title  = {Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices},
  author = {Huancheng Chen and Haris Vikalo},
  journal= {arXiv preprint arXiv:2311.18129},
  year   = {2023}
}
R2 v1 2026-06-28T13:36:12.294Z