GCondenser: Benchmarking Graph Condensation

Large-scale graphs are valuable for graph representation learning, yet the abundant data in these graphs hinders the efficiency of the training process. Graph condensation (GC) alleviates this issue by compressing the large graph into a significantly smaller one that still supports effective model training. Although recent research has introduced various approaches to improve the effectiveness of the condensed graph, evaluations in a more comprehensive and practical manner are not sufficiently explored. This paper proposes the first large-scale graph condensation benchmark, GCondenser, to holistically evaluate and compare mainstream GC methods. GCondenser includes a standardised GC paradigm with condensation, validation, and evaluation procedures, as well as straightforward extensions to new GC methods and datasets. Furthermore, a comprehensive study of GC methods is conducted, presenting insights into the different dimensions of condensation effectiveness.