Rate-Constrained Quantization for Communication-Efficient Federated Learning

TL;DR

This paper introduces RC-FED, a novel federated learning framework that optimizes gradient quantization under both fidelity and data rate constraints, enabling a tunable trade-off between accuracy and communication efficiency.

Contribution

It develops a joint optimization framework for rate-constrained quantization in federated learning, addressing the gap in existing methods that ignore data rate effects.

Findings

RC-FED achieves lower quantization distortion for a given data rate.

The framework demonstrates superior convergence and accuracy compared to baseline methods.

It provides a tunable mechanism to balance communication cost and model fidelity.

Abstract

Quantization is a common approach to mitigate the communication cost of federated learning (FL). In practice, the quantized local parameters are further encoded via an entropy coding technique, such as Huffman coding, for efficient data compression. In this case, the exact communication overhead is determined by the bit rate of the encoded gradients. Recognizing this fact, this work deviates from the existing approaches in the literature and develops a novel quantized FL framework, called \textbf{r}ate-\textbf{c}onstrained \textbf{fed}erated learning (RC-FED), in which the gradients are quantized subject to both fidelity and data rate constraints. We formulate this scheme, as a joint optimization in which the quantization distortion is minimized while the rate of encoded gradients is kept below a target threshold. This enables for a tunable trade-off between quantization distortion and communication cost. We analyze the convergence behavior of RC-FED, and show its superior performance against baseline quantized FL schemes on several datasets.