arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.00136cs.LGcs.AImath.ATmath.KTmath.SG
收藏

学习拓扑保持的数据表示

Learning Topology-Preserving Data Representations

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院);Artificial Intelligence Research Institute (AIRI)(人工智能研究院(AIRI));Huawei Noah’s Ark lab(华为诺亚方舟实验室);CNRS(法国国家科学研究中心);Université Paris Cité(巴黎西岱大学)

Ilya Trofimov, Daniil Cherniavskii, Eduard Tulchinskii, Nikita Balabin, Evgeny Burnaev, Serguei Barannikov

AI总结:

本研究提出一种基于最小化表示拓扑散度(RTD)的自编码器方法RTD-AE,用于学习拓扑保持的低维数据表示,在多项拓扑与结构评估指标上优于现有最先进方法。

摘要:

我们提出了一种学习拓扑保持的数据表示(降维)的方法。该方法旨在通过强制拓扑特征(簇、环、二维空洞等)及其定位的相似性,实现数据流形与其潜在表示之间的拓扑相似性。该方法的核心是最小化原始高维数据与潜在空间中低维表示之间的表示拓扑散度(Representation Topology Divergence,RTD)。RTD最小化可在强理论保证下实现拓扑特征的相近性。我们开发了一种RTD微分方案,并将其用作自编码器的损失项。所提出的方法“RTD-AE”在保持数据流形的全局结构和拓扑方面优于现有最先进的竞品,评估指标包括线性相关性、三元组距离排序准确率以及持久条形码之间的Wasserstein距离。

英文摘要:

We propose a method for learning topology-preserving data representations (dimensionality reduction). The method aims to provide topological similarity between the data manifold and its latent representation via enforcing the similarity in topological features (clusters, loops, 2D voids, etc.) and their localization. The core of the method is the minimization of the Representation Topology Divergence (RTD) between original high-dimensional data and low-dimensional representation in latent space. RTD minimization provides closeness in topological features with strong theoretical guarantees. We develop a scheme for RTD differentiation and apply it as a loss term for the autoencoder. The proposed method "RTD-AE" better preserves the global structure and topology of the data manifold than state-of-the-art competitors as measured by linear correlation, triplet distance ranking accuracy, and Wasserstein distance between persistence barcodes.

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。

↑