PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures

TL;DR

This paper introduces PersLay, a neural network layer designed for persistence diagrams, enabling effective learning from topological signatures of graphs, and demonstrates its competitive performance on graph classification tasks.

Contribution

The paper proposes a versatile neural network layer for learning from persistence diagrams, bridging topological data analysis and machine learning for graph data.

Findings

Achieved competitive classification scores on real-world graph datasets.

Provided a stable encoding of graphs via persistence diagrams using heat kernel signatures.

Unified various vectorization techniques within a single framework.

Abstract

Persistence diagrams, the most common descriptors of Topological Data Analysis, encode topological properties of data and have already proved pivotal in many different applications of data science. However, since the (metric) space of persistence diagrams is not Hilbert, they end up being difficult inputs for most Machine Learning techniques. To address this concern, several vectorization methods have been put forward that embed persistence diagrams into either finite-dimensional Euclidean space or (implicit) infinite dimensional Hilbert space with kernels. In this work, we focus on persistence diagrams built on top of graphs. Relying on extended persistence theory and the so-called heat kernel signature, we show how graphs can be encoded by (extended) persistence diagrams in a provably stable way. We then propose a general and versatile framework for learning vectorizations of persistence diagrams, which encompasses most of the vectorization techniques used in the literature. We finally showcase the experimental strength of our setup by achieving competitive scores on classification tasks on real-life graph datasets.