A Survey on Graph Condensation

TL;DR

This survey comprehensively reviews graph condensation techniques, categorizing methods, analyzing datasets, and discussing challenges to guide future research in reducing large-scale graph data efficiently.

Contribution

It provides a formal definition, taxonomy, and classification of graph condensation methods, along with analysis of datasets and evaluation metrics.

Findings

Classifies GC methods into three types based on objectives

Distinguishes between modifying original graphs and creating synthetic ones

Identifies key challenges and future research directions

Abstract

Analytics on large-scale graphs have posed significant challenges to computational efficiency and resource requirements. Recently, Graph condensation (GC) has emerged as a solution to address challenges arising from the escalating volume of graph data. The motivation of GC is to reduce the scale of large graphs to smaller ones while preserving essential information for downstream tasks. For a better understanding of GC and to distinguish it from other related topics, we present a formal definition of GC and establish a taxonomy that systematically categorizes existing methods into three types based on its objective, and classify the formulations to generate the condensed graphs into two categories as modifying the original graphs or synthetic completely new ones. Moreover, our survey includes a comprehensive analysis of datasets and evaluation metrics in this field. Finally, we conclude by addressing challenges and limitations, outlining future directions, and offering concise guidelines to inspire future research in this field.