FedOUI: OUI-Guided Client Weighting for Federated Aggregation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916003897671680 |
|---|---|
| author | Fernández-Hernández, Alberto Mestre, Jose I. Pérez-Corral, Cristian Dolz, Manuel F. Duato, Jose Quintana-Ortí, Enrique S. |
| author_facet | Fernández-Hernández, Alberto Mestre, Jose I. Pérez-Corral, Cristian Dolz, Manuel F. Duato, Jose Quintana-Ortí, Enrique S. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11571 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FedOUI: OUI-Guided Client Weighting for Federated Aggregation Fernández-Hernández, Alberto Mestre, Jose I. Pérez-Corral, Cristian Dolz, Manuel F. Duato, Jose Quintana-Ortí, Enrique S. Machine Learning 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. |
| title | FedOUI: OUI-Guided Client Weighting for Federated Aggregation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.11571 |