GC-Bench: An Open and Unified Benchmark for Graph Condensation

TL;DR

GC-Bench provides a comprehensive evaluation framework for graph condensation methods, systematically analyzing their effectiveness, transferability, and complexity across diverse datasets, and offering a library to facilitate reproducible research.

Contribution

This paper introduces GC-Bench, the first unified benchmark for evaluating graph condensation algorithms across multiple scenarios and tasks.

Findings

Evaluated 12 state-of-the-art GC algorithms systematically.

Analyzed performance across 12 diverse graph datasets.

Provided an open-source library for reproducible research.

Abstract

Graph condensation (GC) has recently garnered considerable attention due to its ability to reduce large-scale graph datasets while preserving their essential properties. The core concept of GC is to create a smaller, more manageable graph that retains the characteristics of the original graph. Despite the proliferation of graph condensation methods developed in recent years, there is no comprehensive evaluation and in-depth analysis, which creates a great obstacle to understanding the progress in this field. To fill this gap, we develop a comprehensive Graph Condensation Benchmark (GC-Bench) to analyze the performance of graph condensation in different scenarios systematically. Specifically, GC-Bench systematically investigates the characteristics of graph condensation in terms of the following dimensions: effectiveness, transferability, and complexity. We comprehensively evaluate 12 state-of-the-art graph condensation algorithms in node-level and graph-level tasks and analyze their performance in 12 diverse graph datasets. Further, we have developed an easy-to-use library for training and evaluating different GC methods to facilitate reproducible research. The GC-Bench library is available at https://github.com/RingBDStack/GC-Bench.