Fair Resource Allocation in Federated Learning
This addresses fairness issues in federated learning for heterogeneous networks, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of unfair accuracy distribution across devices in federated learning by proposing q-Fair Federated Learning (q-FFL), which encourages more uniform accuracy, and shows that it outperforms existing baselines in fairness, flexibility, and efficiency on federated datasets.
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.