Sliced Wasserstein Kernel for Persistence Diagrams

ICML 2017  ·  Mathieu Carrière, Marco Cuturi, Steve Oudot ·

Persistence diagrams (PDs) play a key role in topological data analysis (TDA), in which they are routinely used to describe topological properties of complicated shapes. PDs enjoy strong stability properties and have proven their utility in various learning contexts. They do not, however, live in a space naturally endowed with a Hilbert structure and are usually compared with specific distances, such as the bottleneck distance. To incorporate PDs in a learning pipeline, several kernels have been proposed for PDs with a strong emphasis on the stability of the RKHS distance w.r.t. perturbations of the PDs. In this article, we use the Sliced Wasserstein approximation SW of the Wasserstein distance to define a new kernel for PDs, which is not only provably stable but also provably discriminative (depending on the number of points in the PDs) w.r.t. the Wasserstein distance $d_1$ between PDs. We also demonstrate its practicality, by developing an approximation technique to reduce kernel computation time, and show that our proposal compares favorably to existing kernels for PDs on several benchmarks.

PDF Abstract ICML 2017 PDF ICML 2017 Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Classification NEURON-Average SW Accuracy 71.20 # 3
Graph Classification NEURON-BINARY SW Accuracy 85.1 # 3
Graph Classification NEURON-MULTI SW Accuracy 57.3 # 2

Methods


No methods listed for this paper. Add relevant methods here