FedFm: Towards a Robust Federated Learning Approach For Fault Mitigation at the Edge Nodes
This addresses reliability issues in federated learning for edge computing, but it appears incremental as it builds on existing fault mitigation concepts.
The paper tackles the problem of edge device failures in federated learning by analyzing the impact of device count and proposing a strategy to select an optimal number of devices, with a mitigation approach to ensure robustness.
Federated Learning deviates from the norm of "send data to model" to "send model to data". When used in an edge ecosystem, numerous heterogeneous edge devices collecting data through different means and connected through different network channels get involved in the training process. Failure of edge devices in such an ecosystem due to device fault or network issues is highly likely. In this paper, we first analyse the impact of the number of edge devices on an FL model and provide a strategy to select an optimal number of devices that would contribute to the model. We observe how the edge ecosystem behaves when the selected devices fail and provide a mitigation strategy to ensure a robust Federated Learning technique.