FedD2S: Personalized Data-Free Federated Knowledge Distillation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929245947691008 |
|---|---|
| author | Atapour, Kawa Seyedmohammadi, S. Jamal Abouei, Jamshid Mohammadi, Arash Plataniotis, Konstantinos N. |
| author_facet | Atapour, Kawa Seyedmohammadi, S. Jamal Abouei, Jamshid Mohammadi, Arash Plataniotis, Konstantinos N. |
| contents | This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework. The model-drift issue, arising from the noniid nature of client data, often results in suboptimal personalization of a global model compared to locally trained models for each client. To tackle this challenge, we propose a novel approach named FedD2S for Personalized Federated Learning (pFL), leveraging knowledge distillation. FedD2S incorporates a deep-to-shallow layer-dropping mechanism in the data-free knowledge distillation process to enhance local model personalization. Through extensive simulations on diverse image datasets-FEMNIST, CIFAR10, CINIC0, and CIFAR100-we compare FedD2S with state-of-the-art FL baselines. The proposed approach demonstrates superior performance, characterized by accelerated convergence and improved fairness among clients. The introduced layer-dropping technique effectively captures personalized knowledge, resulting in enhanced performance compared to alternative FL models. Moreover, we investigate the impact of key hyperparameters, such as the participation ratio and layer-dropping rate, providing valuable insights into the optimal configuration for FedD2S. The findings demonstrate the efficacy of adaptive layer-dropping in the knowledge distillation process to achieve enhanced personalization and performance across diverse datasets and tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10846 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedD2S: Personalized Data-Free Federated Knowledge Distillation Atapour, Kawa Seyedmohammadi, S. Jamal Abouei, Jamshid Mohammadi, Arash Plataniotis, Konstantinos N. Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Image and Video Processing This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework. The model-drift issue, arising from the noniid nature of client data, often results in suboptimal personalization of a global model compared to locally trained models for each client. To tackle this challenge, we propose a novel approach named FedD2S for Personalized Federated Learning (pFL), leveraging knowledge distillation. FedD2S incorporates a deep-to-shallow layer-dropping mechanism in the data-free knowledge distillation process to enhance local model personalization. Through extensive simulations on diverse image datasets-FEMNIST, CIFAR10, CINIC0, and CIFAR100-we compare FedD2S with state-of-the-art FL baselines. The proposed approach demonstrates superior performance, characterized by accelerated convergence and improved fairness among clients. The introduced layer-dropping technique effectively captures personalized knowledge, resulting in enhanced performance compared to alternative FL models. Moreover, we investigate the impact of key hyperparameters, such as the participation ratio and layer-dropping rate, providing valuable insights into the optimal configuration for FedD2S. The findings demonstrate the efficacy of adaptive layer-dropping in the knowledge distillation process to achieve enhanced personalization and performance across diverse datasets and tasks. |
| title | FedD2S: Personalized Data-Free Federated Knowledge Distillation |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Image and Video Processing |
| url | https://arxiv.org/abs/2402.10846 |