Deep Hierarchy Quantization Compression algorithm based on Dynamic Sampling
This addresses network efficiency in federated learning for applications requiring data security, but it is incremental as it builds on existing quantization and sampling techniques.
The paper tackles the network bandwidth load from model parameter transmission in federated learning by proposing a deep hierarchical quantization compression algorithm and dynamic client sampling, which reduces network load and accelerates convergence, as demonstrated on public datasets.
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.