Graph condensation (GC) is an emerging technique designed to learn a significantly smaller graph that retains the essential information of the original graph. Despite the rapid development of GC methods, a systematic evaluation framework remains absent, which is necessary to clarify the critical designs for particular evaluative aspects. Furthermore, several meaningful questions have not been investigated, such as whether GC inherently preserves certain graph properties and offers robustness even without targeted design efforts. Here, we introduce GC-Bench, a comprehensive framework to evaluate recent GC methods across multiple dimensions and generate new insights. Our experimental findings provide deeper insights into the GC process and the characteristics of condensed graphs, guiding future efforts in enhancing performance and exploring new applications.
Please see requirements.txt.
All the scripts are in benchmark folder.
For Table 1 7 8, use sh performacne.sh.
For Figure 3, use sh scalability.sh.
For Figure 4, use sh data_initialization.sh.
For Figure 5 9, use sh transferability.sh.
For Table 2, use sh nas.sh.
For Table 3 10 11, use sh graph_property_preservation.sh.
For Table 4 12, use sh robustness.sh.