arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.08059cs.LGcs.ITmath.ITstat.ML
收藏

联合主成分分析

Federated Principal Component Analysis

University of Cambridge(剑桥大学);Quine Technologies(奎因科技);Alan Turing Institute(艾伦·图灵研究所)

Andreas Grammenos, Rodrigo Mendoza-Smith, Jon Crowcroft, Cecilia Mascolo

摘要:

我们提出了一个联合的,异步的,和$(\varepsilon, δ)$差分私有算法PCA在内存有限的设置。我们的算法增量计算本地模型更新使用流程序,并自适应地估计其$r$领先的主成分时,只有$\mathcal{O}(dr)$内存是可用的$d$是数据的维数。我们通过一个输入扰动方案来保证差分隐私,在该方案中,数据集$\mathbf{X} \in \mathbb{R}^{d \times n}$的协方差矩阵被$\mathcal{O}\left(\left(\frac{d}{n}\right)^2 \log d \right)$中具有方差的非对称随机高斯矩阵扰动,从而改进了现有技术。此外,与以前的PCA联邦或分布式算法相反,我们的算法对输入数据中的排列也是不变的,这提供了对落后或故障节点的鲁棒性。数值模拟表明,在使用有限的内存,我们的算法表现出的性能,密切配合或优于传统的非联邦算法,在没有通信延迟,它表现出有吸引力的水平可扩展性。

英文摘要:

We present a federated, asynchronous, and $(\varepsilon, δ)$-differentially private algorithm for PCA in the memory-limited setting. Our algorithm incrementally computes local model updates using a streaming procedure and adaptively estimates its $r$ leading principal components when only $\mathcal{O}(dr)$ memory is available with $d$ being the dimensionality of the data. We guarantee differential privacy via an input-perturbation scheme in which the covariance matrix of a dataset $\mathbf{X} \in \mathbb{R}^{d \times n}$ is perturbed with a non-symmetric random Gaussian matrix with variance in $\mathcal{O}\left(\left(\frac{d}{n}\right)^2 \log d \right)$, thus improving upon the state-of-the-art. Furthermore, contrary to previous federated or distributed algorithms for PCA, our algorithm is also invariant to permutations in the incoming data, which provides robustness against straggler or failed nodes. Numerical simulations show that, while using limited-memory, our algorithm exhibits performance that closely matches or outperforms traditional non-federated algorithms, and in the absence of communication latency, it exhibits attractive horizontal scalability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑