Keep It Simple: Fault Tolerance Evaluation of Federated Learning with Unreliable Clients
This work addresses fault tolerance for federated learning applications, but it appears incremental as it focuses on evaluation rather than new methods.
The paper tackled the problem of evaluating fault tolerance in federated learning with unreliable clients, finding that simple FL algorithms perform surprisingly well in such scenarios, though no concrete numbers are provided.
Federated learning (FL), as an emerging artificial intelligence (AI) approach, enables decentralized model training across multiple devices without exposing their local training data. FL has been increasingly gaining popularity in both academia and industry. While research works have been proposed to improve the fault tolerance of FL, the real impact of unreliable devices (e.g., dropping out, misconfiguration, poor data quality) in real-world applications is not fully investigated. We carefully chose two representative, real-world classification problems with a limited numbers of clients to better analyze FL fault tolerance. Contrary to the intuition, simple FL algorithms can perform surprisingly well in the presence of unreliable clients.