SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead

Minsu Kim, Walid Saad, Merouane Abdelkader DEBBAH, Choong Seon Hong

Keywords: Federated Learning, Communication and Computation Efficiency, Pruning

TL;DR: We find optimal structured sparse models by communicating trainable thresholds

Abstract:

The large communication and computation overhead of federated learning (FL) is one of the main challenges facing its practical deployment over resource-constrained clients and systems. In this work, SpaFL: a communication-efficient FL framework is proposed to optimize sparse model structures with low computational overhead. In SpaFL, a trainable threshold is defined for each filter/neuron to prune its all connected
parameters, thereby leading to structured sparsity. To optimize the pruning process itself, only thresholds are communicated between a server and clients instead of parameters, thereby learning how to prune. Further, global thresholds are used to update model parameters by extracting aggregated parameter importance. The generalization bound of SpaFL is also derived, thereby proving key insights on the relation between sparsity and performance. Experimental results show that SpaFL improves accuracy while requiring much less communication and computing resources compared to sparse baselines. The code is available at https://github.com/news-vt/SpaFL_NeruIPS_2024

Primary Area: Other (please use sparingly, only use the keyword field for more details)

Submission Number: 13123