Robust Semi-Decentralized Federated Learning via Collaborative Relaying | IEEE Journals & Magazine | IEEE Xplore

Robust Semi-Decentralized Federated Learning via Collaborative Relaying


Abstract:

Intermittent connectivity of clients to the parameter server (PS) is a major bottleneck in federated edge learning frameworks. The lack of constant connectivity induces a...Show More

Abstract:

Intermittent connectivity of clients to the parameter server (PS) is a major bottleneck in federated edge learning frameworks. The lack of constant connectivity induces a large generalization gap, especially when the local data distribution amongst clients exhibits heterogeneity. To overcome intermittent communication outages between clients and the central PS, we introduce the concept of collaborative relaying wherein the participating clients relay their neighbors’ local updates to the PS in order to boost the participation of clients with poor connectivity to the PS. We propose a semi-decentralized federated learning framework in which at every communication round, each client initially computes a local averaging of a subset of its neighboring clients’ updates, and eventually transmits to the PS a weighted average of its own update and those of its neighbors’. We appropriately optimize these local averaging weights to ensure that the global update at the PS is unbiased with minimal variance – consequently improving the convergence rate. Numerical evaluations on the CIFAR-10 dataset demonstrate that our collaborative relaying approach outperforms federated averaging-based benchmarks for learning over intermittently-connected networks such as when the clients communicate over millimeter wave channels with intermittent blockages.
Published in: IEEE Transactions on Wireless Communications ( Volume: 23, Issue: 7, July 2024)
Page(s): 7520 - 7536
Date of Publication: 19 December 2023

ISSN Information:

Funding Agency:


References

References is not available for this document.