arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.16715cs.LG
收藏

GC4NC:面向节点分类的图压缩基准框架与新见解

GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights

Emory University(埃默里大学);Google Deepmind(谷歌DeepMind)

Shengbo Gong, Juntong Ni, Noveen Sachdeva, Carl Yang, Wei Jin

AI总结:

本文提出GC4NC基准框架,从性能、效率、隐私、去噪、NAS和可迁移性等维度系统评估节点分类的图压缩方法,揭示关键设计选择并提供新见解。

摘要:

图压缩(GC)是一种新兴技术,旨在学习一个显著更小的图,同时保留原始图的基本信息。这种压缩图在加速图神经网络方面展现出潜力,同时保持与使用原始较大图所达到的性能相当。此外,该技术还促进了下游应用,如神经架构搜索,并加深了我们对大图中冗余的理解。尽管GC方法发展迅速,特别是在节点分类方面,但仍缺乏统一的评估框架来系统地比较不同的GC方法或阐明提高其有效性的关键设计选择。为了弥补这些差距,我们引入了GC4NC,这是一个全面的框架,用于在多个维度上评估节点分类的各种GC方法,包括性能、效率、隐私保护、去噪能力、神经架构搜索(NAS)有效性和可迁移性。我们的系统评估提供了关于压缩图行为方式以及驱动其成功的关键设计选择的新见解。这些发现为GC方法的未来发展铺平了道路,既提升了性能,又扩展了其实际应用。我们的代码可在https://github.com/Emory-Melody/GraphSlim/tree/main/benchmark获取。

英文摘要:

Graph condensation (GC) is an emerging technique designed to learn a significantly smaller graph that retains the essential information of the original graph. This condensed graph has shown promise in accelerating graph neural networks while preserving performance comparable to those achieved with the original, larger graphs. Additionally, this technique facilitates downstream applications like neural architecture search and deepens our understanding of redundancies in large graphs. Despite the rapid development of GC methods, particularly for node classification, a unified evaluation framework is still lacking to systematically compare different GC methods or clarify key design choices for improving their effectiveness. To bridge these gaps, we introduce \textbf{GC4NC}, a comprehensive framework for evaluating diverse GC methods on node classification across multiple dimensions including performance, efficiency, privacy preservation, denoising ability, NAS effectiveness, and transferability. Our systematic evaluation offers novel insights into how condensed graphs behave and the critical design choices that drive their success. These findings pave the way for future advancements in GC methods, enhancing both performance and expanding their real-world applications. Our code is available at https://github.com/Emory-Melody/GraphSlim/tree/main/benchmark.

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。

↑