FedControl: When Control Theory Meets Federated Learning
This work addresses federated learning efficiency for distributed systems, but it appears incremental as it builds on existing methods with a new control-based approach.
The paper tackles the problem of improving federated learning by differentiating client contributions based on local learning performance and its evolution, inspired by control theory, and demonstrates its classification performance in IID settings compared to FedAvg.
To date, the most popular federated learning algorithms use coordinate-wise averaging of the model parameters. We depart from this approach by differentiating client contributions according to the performance of local learning and its evolution. The technique is inspired from control theory and its classification performance is evaluated extensively in IID framework and compared with FedAvg.