Federated Learning with Hypergradient-based Online Update of Aggregation Weights
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_ | 1866909007725199360 |
|---|---|
| author | Nakai-Kasai, Ayano Wadayama, Tadashi |
| author_facet | Nakai-Kasai, Ayano Wadayama, Tadashi |
| contents | Federated learning using mobile and Internet of Things devices requires not only the ability to handle heterogeneity of clients' data distributions but also high adaptability to varying communication environments. We propose FedHAW (Federated Learning with Hypergradient-based update of Aggregation Weights) that implements online updates of aggregation weights. FedHAW updates the aggregation weights by using hypergradient, the gradient of the objective function with respect to the weights, which can be calculated with low computational overhead. Simulation results show that the proposed method possesses high generalization performance in heterogeneous environments and high robustness to communication errors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00458 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Federated Learning with Hypergradient-based Online Update of Aggregation Weights Nakai-Kasai, Ayano Wadayama, Tadashi Machine Learning Signal Processing Federated learning using mobile and Internet of Things devices requires not only the ability to handle heterogeneity of clients' data distributions but also high adaptability to varying communication environments. We propose FedHAW (Federated Learning with Hypergradient-based update of Aggregation Weights) that implements online updates of aggregation weights. FedHAW updates the aggregation weights by using hypergradient, the gradient of the objective function with respect to the weights, which can be calculated with low computational overhead. Simulation results show that the proposed method possesses high generalization performance in heterogeneous environments and high robustness to communication errors. |
| title | Federated Learning with Hypergradient-based Online Update of Aggregation Weights |
| topic | Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2605.00458 |