# FedOUI: OUI-Guided Client Weighting for Federated Aggregation

Source: [FedOUI: OUI-Guided Client Weighting for Federated Aggregation](<https://www.sota2.com/research/paper/6a0405c0dbc836b87d82774f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-14T05:00:05.131Z

Authors: Alberto Fern\\'andez-Hern\\'andez, Jose I. Mestre, Cristian P\\'erez-Corral, Manuel F. Dolz, Jose Duato, Enrique S. Quintana-Ort\\'i

Published: 2026-05-12T05:59:23.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-10 Strong Non-IID Dirichlet 0.1](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-strong-non-iid-dirichlet-0-1.md>): Image Classification; CIFAR-10 Strong Non-IID Dirichlet 0.1; Final Accuracy: 23.43.

- [Image Classification on CIFAR-10 noisy-client](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-noisy-client.md>): Image Classification; CIFAR-10 noisy-client; Final Accuracy: 23.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.11571>)

[PDF](<https://arxiv.org/pdf/2605.11571.pdf>)
