On the Convergence of Heterogeneous Federated Learning with Arbitrary Adaptive Online Model Pruning. (arXiv:2201.11803v1 [cs.LG])

Web: http://arxiv.org/abs/2201.11803

One of the biggest challenges in Federated Learning (FL) is that client
devices often have drastically different computation and communication
resources for local updates. To this end, recent research efforts have focused
on training heterogeneous local models obtained by pruning a shared global
model. Despite empirical success, theoretical guarantees on convergence remain
an open question. In this paper, we present a unifying framework for
heterogeneous FL algorithms with {\em arbitrary} adaptive online model pruning
and provide a general convergence analysis. …

arxiv convergence federated learning learning model online