Leveraging Foundation Models for Efficient Federated Learning in Resource-restricted Edge Networks
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_ | 1866912028587720704 |
|---|---|
| author | Atapour, S. Kawa SeyedMohammadi, S. Jamal Sheikholeslami, S. Mohammad Abouei, Jamshid Plataniotis, Konstantinos N. Mohammadi, Arash |
| author_facet | Atapour, S. Kawa SeyedMohammadi, S. Jamal Sheikholeslami, S. Mohammad Abouei, Jamshid Plataniotis, Konstantinos N. Mohammadi, Arash |
| contents | Recently pre-trained Foundation Models (FMs) have been combined with Federated Learning (FL) to improve training of downstream tasks while preserving privacy. However, deploying FMs over edge networks with resource-constrained Internet of Things (IoT) devices is under-explored. This paper proposes a novel framework, namely, Federated Distilling knowledge to Prompt (FedD2P), for leveraging the robust representation abilities of a vision-language FM without deploying it locally on edge devices. This framework distills the aggregated knowledge of IoT devices to a prompt generator to efficiently adapt the frozen FM for downstream tasks. To eliminate the dependency on a public dataset, our framework leverages perclass local knowledge from IoT devices and linguistic descriptions of classes to train the prompt generator. Our experiments on diverse image classification datasets CIFAR, OxfordPets, SVHN, EuroSAT, and DTD show that FedD2P outperforms the baselines in terms of model performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09273 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Foundation Models for Efficient Federated Learning in Resource-restricted Edge Networks Atapour, S. Kawa SeyedMohammadi, S. Jamal Sheikholeslami, S. Mohammad Abouei, Jamshid Plataniotis, Konstantinos N. Mohammadi, Arash Distributed, Parallel, and Cluster Computing Machine Learning Recently pre-trained Foundation Models (FMs) have been combined with Federated Learning (FL) to improve training of downstream tasks while preserving privacy. However, deploying FMs over edge networks with resource-constrained Internet of Things (IoT) devices is under-explored. This paper proposes a novel framework, namely, Federated Distilling knowledge to Prompt (FedD2P), for leveraging the robust representation abilities of a vision-language FM without deploying it locally on edge devices. This framework distills the aggregated knowledge of IoT devices to a prompt generator to efficiently adapt the frozen FM for downstream tasks. To eliminate the dependency on a public dataset, our framework leverages perclass local knowledge from IoT devices and linguistic descriptions of classes to train the prompt generator. Our experiments on diverse image classification datasets CIFAR, OxfordPets, SVHN, EuroSAT, and DTD show that FedD2P outperforms the baselines in terms of model performance. |
| title | Leveraging Foundation Models for Efficient Federated Learning in Resource-restricted Edge Networks |
| topic | Distributed, Parallel, and Cluster Computing Machine Learning |
| url | https://arxiv.org/abs/2409.09273 |