.png){kind=icon}
返回
Fedpower: privacy-preserving distributed eigenspace estimation
.png){kind=icon}
PRE
AI
DOI：10.1007/s10994-024-06620-0.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Eigenspace estimation is a fundamental tool in data analytics, which has found applications in PCA, dimension reduction, and clustering, among others. The modern machine learning community usually involves data that come from and belong to different organizations. The low communication power and possible data privacy breaches make the eigenspace estimation challenging. To address these issues, we propose a class of algorithms called FedPower within the federated learning (FL) framework. FedPower leverages the well-known power method by alternating multiple local power iterations and a global aggregation step, thus improving communication efficiency. In the aggregation, we propose to weight each local eigenvector matrix with Orthogonal Procrustes Transformation (OPT) for better alignment. We add Gaussian noise in each iteration to ensure strong privacy protection by adopting the notion of differential privacy (DP). We provide convergence bounds for FedPower composed of different interpretable terms corresponding to the effects of Gaussian noise, parallelization, and random sampling of local machines. Additionally, we conduct experiments to demonstrate the effectiveness of our proposed algorithms.
Keyword:
Communication efficiency
Federated learning
Power method
Stragglers' effect
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
.png){kind=icon}
分享收藏Economic benefit evaluation method for the micro-grid renewable energy system operation微网可再生能源系统运行经济效益评价方法
PREAI
分享收藏分享收藏Photoelectrocatalytic activity PbO2 loaded highly oriented TiO2 nanotubes arrays光电催化活性PbO2负载高取向TiO2纳米管阵列
PREAI
分享收藏
查看更多内容