Conflict-Aware Client Selection for Multi-Server Federated Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911416703778816 |
|---|---|
| author | Hong, Mingwei Lin, Zheng Lin, Zehang Li, Lin Yang, Miao Du, Xia Fang, Zihan Kang, Zhaolu Luan, Dianxin Zhu, Shunzhi |
| author_facet | Hong, Mingwei Lin, Zheng Lin, Zehang Li, Lin Yang, Miao Du, Xia Fang, Zihan Kang, Zhaolu Luan, Dianxin Zhu, Shunzhi |
| contents | Federated learning (FL) has emerged as a promising distributed machine learning (ML) that enables collaborative model training across clients without exposing raw data, thereby preserving user privacy and reducing communication costs. Despite these benefits, traditional single-server FL suffers from high communication latency due to the aggregation of models from a large number of clients. While multi-server FL distributes workloads across edge servers, overlapping client coverage and uncoordinated selection often lead to resource contention, causing bandwidth conflicts and training failures. To address these limitations, we propose a decentralized reinforcement learning with conflict risk prediction, named RL CRP, to optimize client selection in multi-server FL systems. Specifically, each server estimates the likelihood of client selection conflicts using a categorical hidden Markov model based on its sparse historical client selection sequence. Then, a fairness-aware reward mechanism is incorporated to promote long-term client participation for minimizing training latency and resource contention. Extensive experiments demonstrate that the proposed RL-CRP framework effectively reduces inter-server conflicts and significantly improves training efficiency in terms of convergence speed and communication cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02458 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Conflict-Aware Client Selection for Multi-Server Federated Learning Hong, Mingwei Lin, Zheng Lin, Zehang Li, Lin Yang, Miao Du, Xia Fang, Zihan Kang, Zhaolu Luan, Dianxin Zhu, Shunzhi Machine Learning Networking and Internet Architecture Federated learning (FL) has emerged as a promising distributed machine learning (ML) that enables collaborative model training across clients without exposing raw data, thereby preserving user privacy and reducing communication costs. Despite these benefits, traditional single-server FL suffers from high communication latency due to the aggregation of models from a large number of clients. While multi-server FL distributes workloads across edge servers, overlapping client coverage and uncoordinated selection often lead to resource contention, causing bandwidth conflicts and training failures. To address these limitations, we propose a decentralized reinforcement learning with conflict risk prediction, named RL CRP, to optimize client selection in multi-server FL systems. Specifically, each server estimates the likelihood of client selection conflicts using a categorical hidden Markov model based on its sparse historical client selection sequence. Then, a fairness-aware reward mechanism is incorporated to promote long-term client participation for minimizing training latency and resource contention. Extensive experiments demonstrate that the proposed RL-CRP framework effectively reduces inter-server conflicts and significantly improves training efficiency in terms of convergence speed and communication cost. |
| title | Conflict-Aware Client Selection for Multi-Server Federated Learning |
| topic | Machine Learning Networking and Internet Architecture |
| url | https://arxiv.org/abs/2602.02458 |