FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916544724860928 |
|---|---|
| author | Slessor, Jordan Kong, Dezheng Tang, Xiaofen Than, Zheng En Kong, Linglong |
| author_facet | Slessor, Jordan Kong, Dezheng Tang, Xiaofen Than, Zheng En Kong, Linglong |
| contents | Federated learning (FL) is a machine learning methodology that involves the collaborative training of a global model across multiple decentralized clients in a privacy-preserving way. Several FL methods are introduced to tackle communication inefficiencies but do not address how to sample participating clients in each round effectively and in a privacy-preserving manner. In this paper, we propose \textit{FedSTaS}, a client and data-level sampling method inspired by \textit{FedSTS} and \textit{FedSampling}. In each federated learning round, \textit{FedSTaS} stratifies clients based on their compressed gradients, re-allocate the number of clients to sample using an optimal Neyman allocation, and sample local data from each participating clients using a data uniform sampling strategy. Experiments on three datasets show that \textit{FedSTaS} can achieve higher accuracy scores than those of \textit{FedSTS} within a fixed number of training rounds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14226 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning Slessor, Jordan Kong, Dezheng Tang, Xiaofen Than, Zheng En Kong, Linglong Machine Learning 68T05 (Primary) 62H30, 62J05 (Secondary) Federated learning (FL) is a machine learning methodology that involves the collaborative training of a global model across multiple decentralized clients in a privacy-preserving way. Several FL methods are introduced to tackle communication inefficiencies but do not address how to sample participating clients in each round effectively and in a privacy-preserving manner. In this paper, we propose \textit{FedSTaS}, a client and data-level sampling method inspired by \textit{FedSTS} and \textit{FedSampling}. In each federated learning round, \textit{FedSTaS} stratifies clients based on their compressed gradients, re-allocate the number of clients to sample using an optimal Neyman allocation, and sample local data from each participating clients using a data uniform sampling strategy. Experiments on three datasets show that \textit{FedSTaS} can achieve higher accuracy scores than those of \textit{FedSTS} within a fixed number of training rounds. |
| title | FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning |
| topic | Machine Learning 68T05 (Primary) 62H30, 62J05 (Secondary) |
| url | https://arxiv.org/abs/2412.14226 |