Topological Deep Learning: A Review of an Emerging Paradigm

Abstract

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.

arXiv comment7 pages and 2 references

References in corpus (9)

• TopologyNet: Topology based deep convolutional neural networks for biomolecular property predictions
• Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening
• A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology
• A persistence landscapes toolbox for topological statistics
• A Survey of Vectorization Methods in Topological Data Analysis
• Persistence paths and signature features in topological data analysis
• The persistence landscape and some of its properties
• Tropical Coordinates on the Space of Persistence Barcodes
• Genomics Data Analysis via Spectral Shape and Topology

Cited by in corpus (3)

• Emergent properties and the multiscale characterization challenge in condensed matter, from crystals to complex materials: a Review
• Identifying weak critical fluctuations of intermittency in heavy-ion collisions with topological machine learning
• TopOC: Topological Deep Learning for Ovarian and Breast Cancer Diagnosis