.png){kind=icon}
返回
Adaptive client selection and model aggregation for heterogeneous federated learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s00530-024-01386-w.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Federated Learning (FL) is a distributed machine learning method that allows multiple clients to collaborate on model training without sharing raw data. However, FL faces challenges with data heterogeneity, leading to reduced model accuracy and slower convergence. Although existing client selection methods can alleviate the above problems, there is still room to improve FL performance. To tackle these problems, we first propose a novel client selection method based on Multi-Armed Bandit (MAB). The method uses the historical training information uploaded by each client to calculate its correlation and contribution. The calculated values are then used to select a set of clients that can bring the most benefit, i.e., maximizing both model accuracy and convergence speed. Second, we propose an adaptive global model aggregation method that utilizes the local training information of selected clients to dynamically assign weights to local model parameters. Extensive experiments on various datasets with different heterogeneous settings demonstrate that our proposed method is effectively improving FL performance compared to several benchmarks.
Keyword:
Federated learning
Client selection
Multi-armed bandit
Model aggregation
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
引用论文
Study of the performance and scalability of federated learning for medical imaging with intermittent clients间歇性客户端医学影像联合学习的性能和可扩展性研究.png)
NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Adsorption and catalytic properties of iron coproporphyrin III complex at the octane|water interface
PREAI
分享收藏Trust-Augmented Deep Reinforcement Learning for Federated Learning Client Selection用于联合学习客户端选择的信任增强深度强化学习OAAI
OAAI分享收藏
Accelerating Federated Learning With Cluster Construction and Hierarchical Aggregation通过集群构建和层次聚合加速联邦学习
PREAI
分享收藏
查看更多内容