Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning
This work addresses communication efficiency for federated learning systems, but it is incremental as it builds on existing FL methods with specific optimizations.
The paper tackles the communication bottleneck in federated learning by introducing dynamic sampling and selective masking methods, achieving reduced communication costs with experiments on image classification and language modeling datasets.
Federated learning (FL) is a novel machine learning setting that enables on-device intelligence via decentralized training and federated optimization. Deep neural networks' rapid development facilitates the learning techniques for modeling complex problems and emerges into federated deep learning under the federated setting. However, the tremendous amount of model parameters burdens the communication network with a high load of transportation. This paper introduces two approaches for improving communication efficiency by dynamic sampling and top-$k$ selective masking. The former controls the fraction of selected client models dynamically, while the latter selects parameters with top-$k$ largest values of difference for federated updating. Experiments on convolutional image classification and recurrent language modeling are conducted on three public datasets to show our proposed methods' effectiveness.