Hyperbolic Benchmarking Unveils Network Topology-Feature Relationship in GNN Performance

TL;DR

This paper introduces a benchmarking framework using hyperbolic space to analyze how graph topology and node features influence GNN performance, providing insights for better model selection based on network properties.

Contribution

It presents a novel hyperbolic space-based benchmarking method that systematically evaluates GNNs across diverse network topologies and features, revealing their performance dependencies.

Findings

GNN performance varies significantly with network topology and feature correlation.

Network properties like clustering and homophily impact GNN effectiveness.

The framework aids in selecting suitable GNN models for specific graph data characteristics.

Abstract

Graph Neural Networks (GNNs) have excelled in predicting graph properties in various applications ranging from identifying trends in social networks to drug discovery and malware detection. With the abundance of new architectures and increased complexity, GNNs are becoming highly specialized when tested on a few well-known datasets. However, how the performance of GNNs depends on the topological and features properties of graphs is still an open question. In this work, we introduce a comprehensive benchmarking framework for graph machine learning, focusing on the performance of GNNs across varied network structures. Utilizing the geometric soft configuration model in hyperbolic space, we generate synthetic networks with realistic topological properties and node feature vectors. This approach enables us to assess the impact of network properties, such as topology-feature correlation, degree distributions, local density of triangles (or clustering), and homophily, on the effectiveness of different GNN architectures. Our results highlight the dependency of model performance on the interplay between network structure and node features, providing insights for model selection in various scenarios. This study contributes to the field by offering a versatile tool for evaluating GNNs, thereby assisting in developing and selecting suitable models based on specific data characteristics.