arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1310.0423stat.MLmath.SP
收藏

基于网络去噪的网络汇总统计量推断

Inference of Network Summary Statistics Through Network Denoising

Prakash Balachandran, Edoardo Airoldi, Eric Kolaczyk

摘要:

考虑观察一个无向网络,它是“噪声”的,在这个意义上,在观察边缘时存在I类和第二类错误。例如,在推断基因组学中的基因调控网络或神经科学中的功能连接网络的背景下,可能会出现这种错误。那么,给定一个观察到的网络,该网络的汇总统计量在多大程度上代表了真实底层网络的类似物?我们是否可以通过考虑观察到的网络边缘中的噪声来更准确地推断这些统计数据?在本文中,我们回答了这两个问题。特别是,我们开发了一种基于频谱的方法,使用邻接矩阵来“去噪”观察到的网络数据,并产生更准确的推理的真实网络的汇总统计。我们通过适当的风险概念的界限,在$L^2$的意义上,我们的方法的性能特征,并通过说明这项工作的实际影响合成和现实世界的数据得出结论。

英文摘要:

Consider observing an undirected network that is `noisy' in the sense that there are Type I and Type II errors in the observation of edges. Such errors can arise, for example, in the context of inferring gene regulatory networks in genomics or functional connectivity networks in neuroscience. Given a single observed network then, to what extent are summary statistics for that network representative of their analogues for the true underlying network? Can we infer such statistics more accurately by taking into account the noise in the observed network edges? In this paper, we answer both of these questions. In particular, we develop a spectral-based methodology using the adjacency matrix to `denoise' the observed network data and produce more accurate inference of the summary statistics of the true network. We characterize performance of our methodology through bounds on appropriate notions of risk in the $L^2$ sense, and conclude by illustrating the practical impact of this work on synthetic and real-world data.

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。

↑