Persistence paths and signature features in topological data analysis

Abstract

We introduce a new feature map for barcodes that arise in persistent homology computation. The main idea is to first realize each barcode as a path in a convenient vector space, and to then compute its path signature which takes values in the tensor algebra of that vector space. The composition of these two operations - barcode to path, path to tensor series - results in a feature map that has several desirable properties for statistical learning, such as universality and characteristicness, and achieves state-of-the-art results on common classification benchmarks.

Additional experiment and further details. To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence

References in corpus (9)

• Scikit-learn: Machine Learning in Python
• The persistent cosmic web and its filamentary structure I: Theory and implementation
• Statistical topological data analysis using persistence landscapes
• A persistence landscapes toolbox for topological statistics
• Sliced Wasserstein Kernel for Persistence Diagrams
• Characteristic functions of measures on geometric rough paths
• Signature moments to characterize laws of stochastic processes
• Kernel Distribution Embeddings: Universal Kernels, Characteristic Kernels and Kernel Metrics on Distributions
• Kernels for sequentially ordered data

Cited by in corpus (20)

• Persistent Homology of Complex Networks for Dynamic State Detection
• A Survey of Vectorization Methods in Topological Data Analysis
• The persistence landscape and some of its properties
• Topological Deep Learning: A Review of an Emerging Paradigm
• Topological Feature Vectors for Chatter Detection in Turning Processes
• Approximating Continuous Functions on Persistence Diagrams Using Template Functions
• On the reorderability of node-filtered order complexes
• Euler Characteristic Curves and Profiles: a stable shape invariant for big data problems
• A persistent homology approach to heart rate variability analysis with an application to sleep-wake classification
• A Primer on the Signature Method in Machine Learning
• Vietoris-Rips Complexes of Regular Polygons
• Signatures in Shape Analysis: an Efficient Approach to Motion Identification
• Feature Engineering with Regularity Structures
• 2-d signature of images and texture classification
• Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions
• Toric geometry of path signature varieties
• Path Signatures on Lie Groups
• On the signature of an image
• Stable and Discriminative Topological Graph Analysis
• From augmented microscopy to the topological transformer: a new approach in cell image analysis for Alzheimer's research