FedControl: When Control Theory Meets Federated Learning

05/27/2022

∙

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.

READ FULL TEXT

FedControl: When Control Theory Meets Federated Learning

Federated Learning Aggregation: New Robust Algorithms with Guarantees

Fine-tuning is Fine in Federated Learning

Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks

A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison

Federated Adaptation of Reservoirs via Intrinsic Plasticity

Fed-Focal Loss for imbalanced data classification in Federated Learning

Information-Theoretic Perspective of Federated Learning

FedControl: When Control Theory Meets Federated Learning

Related Research

Federated Learning Aggregation: New Robust Algorithms with Guarantees

Fine-tuning is Fine in Federated Learning

Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks

A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison

Federated Adaptation of Reservoirs via Intrinsic Plasticity

Fed-Focal Loss for imbalanced data classification in Federated Learning

Information-Theoretic Perspective of Federated Learning