Efficient Client Selection in Federated Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917908277362688 |
|---|---|
| author | Marfo, William Tosh, Deepak K. Moore, Shirley V. |
| author_facet | Marfo, William Tosh, Deepak K. Moore, Shirley V. |
| contents | Federated Learning (FL) enables decentralized machine learning while preserving data privacy. This paper proposes a novel client selection framework that integrates differential privacy and fault tolerance. The adaptive client selection adjusts the number of clients based on performance and system constraints, with noise added to protect privacy. Evaluated on the UNSW-NB15 and ROAD datasets for network anomaly detection, the method improves accuracy by 7% and reduces training time by 25% compared to baselines. Fault tolerance enhances robustness with minimal performance trade-offs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00036 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Client Selection in Federated Learning Marfo, William Tosh, Deepak K. Moore, Shirley V. Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Federated Learning (FL) enables decentralized machine learning while preserving data privacy. This paper proposes a novel client selection framework that integrates differential privacy and fault tolerance. The adaptive client selection adjusts the number of clients based on performance and system constraints, with noise added to protect privacy. Evaluated on the UNSW-NB15 and ROAD datasets for network anomaly detection, the method improves accuracy by 7% and reduces training time by 25% compared to baselines. Fault tolerance enhances robustness with minimal performance trade-offs. |
| title | Efficient Client Selection in Federated Learning |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2502.00036 |