Sparse Random Networks for Communication-Efficient Federated Learning
This addresses communication efficiency for federated learning systems, but it is a novel method for a known bottleneck rather than a new paradigm.
The paper tackles the high communication cost in federated learning by proposing a method that freezes weights at random initial values and trains a stochastic binary mask to find an optimal sparse random network, resulting in improvements in accuracy, communication (less than 1 bit per parameter), convergence speed, and model size across multiple datasets.
One main challenge in federated learning is the large communication cost of exchanging weight updates from clients to the server at each round. While prior work has made great progress in compressing the weight updates through gradient compression methods, we propose a radically different approach that does not update the weights at all. Instead, our method freezes the weights at their initial \emph{random} values and learns how to sparsify the random network for the best performance. To this end, the clients collaborate in training a \emph{stochastic} binary mask to find the optimal sparse random network within the original one. At the end of the training, the final model is a sparse network with random weights -- or a subnetwork inside the dense random network. We show improvements in accuracy, communication (less than $1$ bit per parameter (bpp)), convergence speed, and final model size (less than $1$ bpp) over relevant baselines on MNIST, EMNIST, CIFAR-10, and CIFAR-100 datasets, in the low bitrate regime under various system configurations.