Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.06497 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915280257548288 |
|---|---|
| author | Wang, Jiacheng Lv, Hongtao Liu, Lei |
| author_facet | Wang, Jiacheng Lv, Hongtao Liu, Lei |
| contents | Traditional Federated Learning (FL) faces significant challenges in terms of efficiency and accuracy, particularly in heterogeneous environments where clients employ diverse model architectures and have varying computational resources. Such heterogeneity complicates the aggregation process, leading to performance bottlenecks and reduced model generalizability. To address these issues, we propose FedADP, a federated learning framework designed to adapt to client heterogeneity by dynamically adjusting model architectures during aggregation. FedADP enables effective collaboration among clients with differing capabilities, maximizing resource utilization and ensuring model quality. Our experimental results demonstrate that FedADP significantly outperforms existing methods, such as FlexiFed, achieving an accuracy improvement of up to 23.30%, thereby enhancing model adaptability and training efficiency in heterogeneous real-world settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06497 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures Wang, Jiacheng Lv, Hongtao Liu, Lei Machine Learning Traditional Federated Learning (FL) faces significant challenges in terms of efficiency and accuracy, particularly in heterogeneous environments where clients employ diverse model architectures and have varying computational resources. Such heterogeneity complicates the aggregation process, leading to performance bottlenecks and reduced model generalizability. To address these issues, we propose FedADP, a federated learning framework designed to adapt to client heterogeneity by dynamically adjusting model architectures during aggregation. FedADP enables effective collaboration among clients with differing capabilities, maximizing resource utilization and ensuring model quality. Our experimental results demonstrate that FedADP significantly outperforms existing methods, such as FlexiFed, achieving an accuracy improvement of up to 23.30%, thereby enhancing model adaptability and training efficiency in heterogeneous real-world settings. |
| title | FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.06497 |