.png){kind=icon}
返回
LoSAC: An Efficient Local Stochastic Average Control Method for Federated Optimization
.png){kind=icon}
OA
AI
DOI：10.1145/3566128.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Federated optimization (FedOpt), which targets at collaboratively training a learning model across a large number of distributed clients, is vital for federated learning. The primary concerns in FedOpt can be attributed to the model divergence and communication efficiency, which significantly affect the performance. In this article, we propose a new method, i.e., LoSAC, to learn from heterogeneous distributed data more efficiently. Its key algorithmic insight is to locally update the estimate for the global full gradient after each regular local model update. Thus, LoSAC can keep clients' information refreshed in a more compact way. In particular, we have studied the convergence result for LoSAC. Besides, the bonus of LoSAC is the ability to defend the information leakage from the recent technique Deep Leakage Gradients (DLG). Finally, experiments have verified the superiority of LoSAC comparing with state-of-the-art FedOpt algorithms. Specifically, LoSAC significantly improves communication efficiency by more than 100% on average, mitigates the model divergence problem, and equips with the defense ability against DLG.
Keyword:
Federated optimization
communication efficiency
data heterogeneity
client sampling
model divergence
期刊
IF:
4.8
论文数:
1.3K
被引数:
4.4K
机构
引用论文
Federated learning of predictive models from federated Electronic Health Records从联邦电子健康记录中联合学习预测模型
OAAI
OAAI分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏分享收藏Energy-efficient load balancing scheme for two-tier communication in wireless sensor networks无线传感器网络中节能的两层通信负载均衡方案
PREAI
分享收藏
查看更多内容