One main challenge in federated learning is the large communication cost of ex-changing 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 random values and learns how to sparsify the random network for the best performance. To this end, the clients collaborate in training a 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 sub-network 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.