arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.03836cs.LGcs.AI
收藏

拓扑深度学习:一个新兴范式的综述

Topological Deep Learning: A Review of an Emerging Paradigm

College of Science, Australian National University(澳大利亚国立大学理学院);CSIRO(联邦科学与工业研究组织)

Ali Zia, Abdelwahed Khamis, James Nichols, Zeeshan Hayder, Vivien Rolland, Lars Petersson

AI总结:

本文综述拓扑深度学习这一新兴范式,回顾TDA核心概念及其与深度学习的整合方式,涵盖分析现有模型的应用,并讨论挑战与未来方向。

摘要:

拓扑数据分析(TDA)提供了对数据形状的洞察。通过这些方法获得的摘要是对多维数据的原理性全局描述,同时展现出诸如对形变和噪声的鲁棒性等稳定性质。这些性质在深度学习流水线中是理想的,但通常是通过非TDA策略获得的。这部分是由于将TDA构造(如条形码和持久性图)与当前深度学习算法结合存在困难。幸运的是,我们现在正见证越来越多采用拓扑引导组件的深度学习应用。在本综述中,我们通过首先回顾TDA的核心概念来审视拓扑深度学习这一新兴领域。然后,我们探讨TDA技术的使用如何随时间演变以支持深度学习框架,以及它们如何被整合到深度学习的不同方面。此外,我们涉及TDA用于分析现有深度模型,即深度拓扑分析。最后,我们讨论拓扑深度学习的挑战和未来前景。

英文摘要:

Topological data analysis (TDA) provides insight into data shape. The summaries obtained by these methods are principled global descriptions of multi-dimensional data whilst exhibiting stable properties such as robustness to deformation and noise. Such properties are desirable in deep learning pipelines but they are typically obtained using non-TDA strategies. This is partly caused by the difficulty of combining TDA constructs (e.g. barcode and persistence diagrams) with current deep learning algorithms. Fortunately, we are now witnessing a growth of deep learning applications embracing topologically-guided components. In this survey, we review the nascent field of topological deep learning by first revisiting the core concepts of TDA. We then explore how the use of TDA techniques has evolved over time to support deep learning frameworks, and how they can be integrated into different aspects of deep learning. Furthermore, we touch on TDA usage for analyzing existing deep models; deep topological analytics. Finally, we discuss the challenges and future prospects of topological deep learning.

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。

↑