Adaptive Client Selection with Personalization for Communication Efficient Federated Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909406372823040 |
|---|---|
| author | de Souza, Allan M. Maciel, Filipe da Costa, Joahannes B. D. Bittencourt, Luiz F. Cerqueira, Eduardo Loureiro, Antonio A. F. Villas, Leandro A. |
| author_facet | de Souza, Allan M. Maciel, Filipe da Costa, Joahannes B. D. Bittencourt, Luiz F. Cerqueira, Eduardo Loureiro, Antonio A. F. Villas, Leandro A. |
| contents | Federated Learning (FL) is a distributed approach to collaboratively training machine learning models. FL requires a high level of communication between the devices and a central server, thus imposing several challenges, including communication bottlenecks and network scalability. This article introduces ACSP-FL (https://github.com/AllanMSouza/ACSP-FL), a solution to reduce the overall communication and computation costs for training a model in FL environments. ACSP-FL employs a client selection strategy that dynamically adapts the number of devices training the model and the number of rounds required to achieve convergence. Moreover, ACSP-FL enables model personalization to improve clients performance. A use case based on human activity recognition datasets aims to show the impact and benefits of ACSP-FL when compared to state-of-the-art approaches. Experimental evaluations show that ACSP-FL minimizes the overall communication and computation overheads to train a model and converges the system efficiently. In particular, ACSP-FL reduces communication up to 95% compared to literature approaches while providing good convergence even in scenarios where data is distributed differently, non-independent and identical way between client devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17833 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Client Selection with Personalization for Communication Efficient Federated Learning de Souza, Allan M. Maciel, Filipe da Costa, Joahannes B. D. Bittencourt, Luiz F. Cerqueira, Eduardo Loureiro, Antonio A. F. Villas, Leandro A. Machine Learning Distributed, Parallel, and Cluster Computing Federated Learning (FL) is a distributed approach to collaboratively training machine learning models. FL requires a high level of communication between the devices and a central server, thus imposing several challenges, including communication bottlenecks and network scalability. This article introduces ACSP-FL (https://github.com/AllanMSouza/ACSP-FL), a solution to reduce the overall communication and computation costs for training a model in FL environments. ACSP-FL employs a client selection strategy that dynamically adapts the number of devices training the model and the number of rounds required to achieve convergence. Moreover, ACSP-FL enables model personalization to improve clients performance. A use case based on human activity recognition datasets aims to show the impact and benefits of ACSP-FL when compared to state-of-the-art approaches. Experimental evaluations show that ACSP-FL minimizes the overall communication and computation overheads to train a model and converges the system efficiently. In particular, ACSP-FL reduces communication up to 95% compared to literature approaches while providing good convergence even in scenarios where data is distributed differently, non-independent and identical way between client devices. |
| title | Adaptive Client Selection with Personalization for Communication Efficient Federated Learning |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2411.17833 |