TopER: Topological Embeddings in Graph Representation Learning

TL;DR

TopER introduces a low-dimensional, topologically grounded graph embedding method that improves interpretability and visualization while maintaining competitive performance in clustering and classification tasks.

Contribution

This paper presents TopER, a novel topological embedding technique based on Persistent Homology that enhances interpretability and visualization of graph data.

Findings

TopER achieves state-of-the-art results in graph classification.

TopER provides intuitive visualizations of complex graph structures.

TopER performs competitively across molecular, biological, and social network datasets.

Abstract

Graph embeddings play a critical role in graph representation learning, allowing machine learning models to explore and interpret graph-structured data. However, existing methods often rely on opaque, high-dimensional embeddings, limiting interpretability and practical visualization. In this work, we introduce Topological Evolution Rate (TopER), a novel, low-dimensional embedding approach grounded in topological data analysis. TopER simplifies a key topological approach, Persistent Homology, by calculating the evolution rate of graph substructures, resulting in intuitive and interpretable visualizations of graph data. This approach not only enhances the exploration of graph datasets but also delivers competitive performance in graph clustering and classification tasks. Our TopER-based models achieve or surpass state-of-the-art results across molecular, biological, and social network datasets in tasks such as classification, clustering, and visualization.