Model
q-FedAvg
A fairness-oriented federated learning algorithm that assigns larger weights to clients with higher losses, thereby improving the performance of disadvantaged clients in heterogeneous federated settings.
Timeline (last 90 days)
Oct 12
The client reweighting method q-FedAvg assigns higher weights to clients with greater loss, but weight adjustment changes the shape of the global loss function, causing the model to deviate from the original aggregation objective.
Unverified50%