arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01828cs.LGstat.ML
收藏

从低维嵌入中分解出先验知识

Factoring out prior knowledge from low-dimensional embeddings

Ghent University(根特大学);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所);Saarland University(萨尔大学);CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全研究中心)

Edith Heiter, Jonas Fischer, Jilles Vreeken

摘要:

低维嵌入技术,如tSNE和UMAP允许可视化高维数据,从而促进有趣结构的发现。虽然它们被广泛使用,但它们将数据可视化为原样,而不是根据我们对数据的背景知识。然而,我们已经知道的东西强烈地决定了什么是新奇的,因此是有趣的。在本文中,我们提出了两种方法分解出先验知识的形式,距离矩阵的低维嵌入。为了从tSNE嵌入中排除先验知识,我们提出了JEDI,它使用Jensen-Shannon散度以原则性的方式适应tSNE目标。为了从任何下游嵌入方法中排除先验知识,我们提出了CONFETTI,其中我们直接对输入距离矩阵进行操作。对合成数据和真实世界数据的大量实验表明,这两种方法都能很好地工作,提供了表现出有意义的结构的嵌入,否则这些结构将保持隐藏。

英文摘要:

Low-dimensional embedding techniques such as tSNE and UMAP allow visualizing high-dimensional data and therewith facilitate the discovery of interesting structure. Although they are widely used, they visualize data as is, rather than in light of the background knowledge we have about the data. What we already know, however, strongly determines what is novel and hence interesting. In this paper we propose two methods for factoring out prior knowledge in the form of distance matrices from low-dimensional embeddings. To factor out prior knowledge from tSNE embeddings, we propose JEDI that adapts the tSNE objective in a principled way using Jensen-Shannon divergence. To factor out prior knowledge from any downstream embedding approach, we propose CONFETTI, in which we directly operate on the input distance matrices. Extensive experiments on both synthetic and real world data show that both methods work well, providing embeddings that exhibit meaningful structure that would otherwise remain hidden.

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。

↑