arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.00615cs.LG
收藏

GC-Bench:一个开放且统一的图凝聚基准

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

Beihang University(北京航空航天大学);University of Edinburgh(爱丁堡大学);Guangxi Normal University(广西师范大学);Zhejiang University(浙江大学)

Qingyun Sun, Ziying Chen, Beining Yang, Cheng Ji, Xingcheng Fu, Sheng Zhou, Hao Peng, Jianxin Li, Philip S. Yu

AI总结:

本文提出GC-Bench基准,系统评估12种图凝聚算法在12个数据集上的有效性、可迁移性和复杂性,并提供开源库以促进可复现研究。

摘要:

图凝聚(GC)由于能够在保留大规模图数据集基本特性的同时对其进行缩减,近年来受到了相当大的关注。GC的核心思想是创建一个更小、更易于管理的图,同时保留原始图的特征。尽管近年来涌现出大量图凝聚方法,但缺乏全面的评估和深入分析,这严重阻碍了对该领域进展的理解。为了填补这一空白,我们开发了一个全面的图凝聚基准(GC-Bench),以系统地分析图凝聚在不同场景下的性能。具体而言,GC-Bench从以下维度系统地考察图凝聚的特性:有效性、可迁移性和复杂性。我们在节点级和图级任务中全面评估了12种最先进的图凝聚算法,并在12个多样化的图数据集上分析了它们的性能。此外,我们还开发了一个易于使用的库,用于训练和评估不同的GC方法,以促进可复现研究。GC-Bench库可在https://github.com/RingBDStack/GC-Bench获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑