GC-Bench: An Open and Unified Benchmark for Graph Condensation
| Autor: | Sun, Qingyun, Chen, Ziying, Yang, Beining, Ji, Cheng, Fu, Xingcheng, Zhou, Sheng, Peng, Hao, Li, Jianxin, Yu, Philip S. |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | 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. Comment: The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Preprint, under review) |
| Databáze: | arXiv |
| Externí odkaz: |
|