Deep Hierarchy Quantization Compression algorithm based on Dynamic Sampling

TL;DR

This paper introduces a deep hierarchical quantization compression algorithm with dynamic sampling for federated learning, significantly reducing network load and accelerating model convergence by compressing model parameters based on data distribution.

Contribution

It proposes a novel hierarchical quantization compression method combined with dynamic client sampling to improve efficiency in federated learning.

Findings

Reduces network bandwidth usage during model transmission.

Accelerates model convergence with dynamic client sampling.

Effective across multiple public datasets.

Abstract

Unlike traditional distributed machine learning, federated learning stores data locally for training and then aggregates the models on the server, which solves the data security problem that may arise in traditional distributed machine learning. However, during the training process, the transmission of model parameters can impose a significant load on the network bandwidth. It has been pointed out that the vast majority of model parameters are redundant during model parameter transmission. In this paper, we explore the data distribution law of selected partial model parameters on this basis, and propose a deep hierarchical quantization compression algorithm, which further compresses the model and reduces the network load brought by data transmission through the hierarchical quantization of model parameters. And we adopt a dynamic sampling strategy for the selection of clients to accelerate the convergence of the model. Experimental results on different public datasets demonstrate the effectiveness of our algorithm.