Optimized Federated Multitask Learning in Mobile Edge Networks: A Hybrid Client Selection and Model Aggregation Approach
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909252165042176 |
|---|---|
| author | Hamood, Moqbel Albaseer, Abdullatif Abdallah, Mohamed Al-Fuqaha, Ala Mohamed, Amr |
| author_facet | Hamood, Moqbel Albaseer, Abdullatif Abdallah, Mohamed Al-Fuqaha, Ala Mohamed, Amr |
| contents | We propose clustered federated multitask learning to address statistical challenges in non-independent and identically distributed data across clients. Our approach tackles complexities in hierarchical wireless networks by clustering clients based on data distribution similarities and assigning specialized models to each cluster. These complexities include slower convergence and mismatched model allocation due to hierarchical model aggregation and client selection. The proposed framework features a two-phase client selection and a two-level model aggregation scheme. It ensures fairness and effective participation using greedy and round-robin methods. Our approach significantly enhances convergence speed, reduces training time, and decreases energy consumption by up to 60%, ensuring clients receive models tailored to their specific data needs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09219 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimized Federated Multitask Learning in Mobile Edge Networks: A Hybrid Client Selection and Model Aggregation Approach Hamood, Moqbel Albaseer, Abdullatif Abdallah, Mohamed Al-Fuqaha, Ala Mohamed, Amr Networking and Internet Architecture We propose clustered federated multitask learning to address statistical challenges in non-independent and identically distributed data across clients. Our approach tackles complexities in hierarchical wireless networks by clustering clients based on data distribution similarities and assigning specialized models to each cluster. These complexities include slower convergence and mismatched model allocation due to hierarchical model aggregation and client selection. The proposed framework features a two-phase client selection and a two-level model aggregation scheme. It ensures fairness and effective participation using greedy and round-robin methods. Our approach significantly enhances convergence speed, reduces training time, and decreases energy consumption by up to 60%, ensuring clients receive models tailored to their specific data needs. |
| title | Optimized Federated Multitask Learning in Mobile Edge Networks: A Hybrid Client Selection and Model Aggregation Approach |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2407.09219 |