Personalized client-edge-cloud hierarchical federated learning in mobile edge computing
Abstract Mobile edge computing aims to deploy mobile applications at the edge of wireless networks. Federated learning in mobile edge computing is a forward-looking distributed framework for deploying deep learning algorithms in many application scenarios. One challenge of federated learning in mobi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-12-01
|
| Series: | Journal of Cloud Computing: Advances, Systems and Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13677-024-00721-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559092762509312 |
|---|---|
| author | Chunmei Ma Xiangqian Li Baogui Huang Guangshun Li Fengyin Li |
| author_facet | Chunmei Ma Xiangqian Li Baogui Huang Guangshun Li Fengyin Li |
| author_sort | Chunmei Ma |
| collection | DOAJ |
| description | Abstract Mobile edge computing aims to deploy mobile applications at the edge of wireless networks. Federated learning in mobile edge computing is a forward-looking distributed framework for deploying deep learning algorithms in many application scenarios. One challenge of federated learning in mobile edge computing is data heterogeneity since the unified model of federated learning performs poorly when client data are non-independent and identically distributed. Personalized federated learning can obtain amazing models in scenarios where client data are non-independent and identically distributed. This is because the personalized model captures the features of users’ local data more accurately than the unified model. The personalized federated learning problem under two-tier (server-client) federated learning structures has been widely studied and applied. However, a lot of research results exhibit three distinct limitations: 1) suboptimal communication efficiency, 2) slow model convergence, and 3) underutilization of the relationships within user data, resulting in lower accuracy of personalized models. In this paper, we present the first personalized federated learning algorithm based on the client-edge-cloud structure. The edge server is responsible for model personalization and employs a learnable mixing parameter to mix the local model and the global model. We also utilize two learnable normalization parameters trained by clients to improve the performance of personalized models. Furthermore, in order to facilitate the collaboration among edge servers, we propose a similarity aggregation method to assign aggregation weights based on the Tanimoto coefficients between models. The experimental results show that the proposed algorithm not only increases the convergence speed of personalized models but also improves their testing accuracy. |
| format | Article |
| id | doaj-art-bd5c75031a0448069b33e90b2432ae75 |
| institution | Kabale University |
| issn | 2192-113X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Cloud Computing: Advances, Systems and Applications |
| spelling | doaj-art-bd5c75031a0448069b33e90b2432ae752025-01-05T12:46:16ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2024-12-0113111710.1186/s13677-024-00721-wPersonalized client-edge-cloud hierarchical federated learning in mobile edge computingChunmei Ma0Xiangqian Li1Baogui Huang2Guangshun Li3Fengyin Li4School of Computer Science, Qufu Normal UniversitySchool of Computer Science, Qufu Normal UniversitySchool of Computer Science, Qufu Normal UniversitySchool of Computer Science, Qufu Normal UniversitySchool of Computer Science, Qufu Normal UniversityAbstract Mobile edge computing aims to deploy mobile applications at the edge of wireless networks. Federated learning in mobile edge computing is a forward-looking distributed framework for deploying deep learning algorithms in many application scenarios. One challenge of federated learning in mobile edge computing is data heterogeneity since the unified model of federated learning performs poorly when client data are non-independent and identically distributed. Personalized federated learning can obtain amazing models in scenarios where client data are non-independent and identically distributed. This is because the personalized model captures the features of users’ local data more accurately than the unified model. The personalized federated learning problem under two-tier (server-client) federated learning structures has been widely studied and applied. However, a lot of research results exhibit three distinct limitations: 1) suboptimal communication efficiency, 2) slow model convergence, and 3) underutilization of the relationships within user data, resulting in lower accuracy of personalized models. In this paper, we present the first personalized federated learning algorithm based on the client-edge-cloud structure. The edge server is responsible for model personalization and employs a learnable mixing parameter to mix the local model and the global model. We also utilize two learnable normalization parameters trained by clients to improve the performance of personalized models. Furthermore, in order to facilitate the collaboration among edge servers, we propose a similarity aggregation method to assign aggregation weights based on the Tanimoto coefficients between models. The experimental results show that the proposed algorithm not only increases the convergence speed of personalized models but also improves their testing accuracy.https://doi.org/10.1186/s13677-024-00721-wMobile edge computingFederated learningClient-edge-cloudPersonalized modelNon-independent and identically distributed |
| spellingShingle | Chunmei Ma Xiangqian Li Baogui Huang Guangshun Li Fengyin Li Personalized client-edge-cloud hierarchical federated learning in mobile edge computing Journal of Cloud Computing: Advances, Systems and Applications Mobile edge computing Federated learning Client-edge-cloud Personalized model Non-independent and identically distributed |
| title | Personalized client-edge-cloud hierarchical federated learning in mobile edge computing |
| title_full | Personalized client-edge-cloud hierarchical federated learning in mobile edge computing |
| title_fullStr | Personalized client-edge-cloud hierarchical federated learning in mobile edge computing |
| title_full_unstemmed | Personalized client-edge-cloud hierarchical federated learning in mobile edge computing |
| title_short | Personalized client-edge-cloud hierarchical federated learning in mobile edge computing |
| title_sort | personalized client edge cloud hierarchical federated learning in mobile edge computing |
| topic | Mobile edge computing Federated learning Client-edge-cloud Personalized model Non-independent and identically distributed |
| url | https://doi.org/10.1186/s13677-024-00721-w |
| work_keys_str_mv | AT chunmeima personalizedclientedgecloudhierarchicalfederatedlearninginmobileedgecomputing AT xiangqianli personalizedclientedgecloudhierarchicalfederatedlearninginmobileedgecomputing AT baoguihuang personalizedclientedgecloudhierarchicalfederatedlearninginmobileedgecomputing AT guangshunli personalizedclientedgecloudhierarchicalfederatedlearninginmobileedgecomputing AT fengyinli personalizedclientedgecloudhierarchicalfederatedlearninginmobileedgecomputing |