FedOUI: OUI-Guided Client Weighting for Federated Aggregation
For federated learning practitioners, FedOUI offers a lightweight and interpretable way to weight clients using internal activation structure, showing gains under strong heterogeneity.
FedOUI introduces a client weighting method for federated aggregation based on the Overfitting-Underfitting Indicator (OUI), an activation-based metric. Under strong non-IID and noisy conditions on CIFAR-10, it improves aggregation quality compared to FedAvg, FedProx, and a gradient-alignment baseline.
Federated learning usually aggregates client updates using dataset size or gradient-level criteria, while overlooking internal signals about how each client model is organizing its input space during training. We introduce FedOUI, a simple aggregation rule based on the Overfitting-Underfitting Indicator (OUI), an activation-based and label-free metric. Each participating client sends its local update together with a OUI value computed on a fixed probe batch, and the server estimates the round-wise OUI distribution to assign lower weights to structurally atypical clients through a smooth reweighting rule. We evaluate FedOUI on CIFAR-10 under strong non-IID partitioning and noisy-client conditions, comparing it with FedAvg, FedProx, and a gradient-alignment baseline. The clearest gains appear under strong heterogeneity, where OUI-based weighting improves aggregation quality while remaining lightweight and interpretable. These results show that internal activation structure can provide useful information for federated aggregation beyond client size and gradient geometry.