Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relaying
This addresses connectivity failures in federated learning for edge computing, offering a solution to boost participation of poorly-connected clients, though it is incremental as it builds on existing federated learning methods.
The paper tackles the problem of intermittent client connectivity in federated edge learning, which causes a large generalization gap, especially with heterogeneous data, by introducing a semi-decentralized framework with collaborative relaying. The result shows that this approach outperforms federated averaging-based benchmarks on the CIFAR-10 dataset, improving convergence rates by ensuring unbiased global updates with minimal variance.
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 consensus 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 consensus 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.