What question did this study set out to answer?

This research aims to enhance fairness in resource allocation within federated learning models.

May 25, 2019Open Access

Fair Resource Allocation in Federated Learning

Key Points

This research aims to enhance fairness in resource allocation within federated learning models.
Proposed q-Fair Federated Learning (q-FFL) optimization objective.
Developed q-FedAvg, a communication-efficient method for federated networks.
Validated on various federated datasets with both convex and non-convex models.
q-FFL improves accuracy distribution across devices compared to existing methods.
q-FedAvg enhances both fairness and efficiency in model training.
Demonstrated better performance in flexibility and effectiveness on tested datasets.

Abstract

Federated learning involves training statistical models in massive, heterogeneous networks. Naively minimizing an aggregate loss function in such a network may disproportionately advantage or disadvantage some of the devices. In this work, we propose q-Fair Federated Learning (q-FFL), a novel optimization objective inspired by fair resource allocation in wireless networks that encourages a more fair (specifically, a more uniform) accuracy distribution across devices in federated networks. To solve q-FFL, we devise a communication-efficient method, q-FedAvg, that is suited to federated networks. We validate both the effectiveness of q-FFL and the efficiency of q-FedAvg on a suite of federated datasets with both convex and non-convex models, and show that q-FFL (along with q-FedAvg) outperforms existing baselines in terms of the resulting fairness, flexibility, and efficiency.

Bookmark

View Full Paper