arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.13200cs.LG
收藏

RobGC:迈向鲁棒的图压缩

RobGC: Towards Robust Graph Condensation

School of Electrical Engineering and Computer Science, the University of Queensland(电气工程与计算机科学学院,昆士兰大学);School of Computer Science, Beijing University of Posts and Telecommunications(计算机科学学院,北京邮电大学);Center for Machine Learning Research, Peking University(机器学习研究中心,北京大学);School of Computer Science, Peking University(计算机科学学院,北京大学)

Xinyi Gao, Hongzhi Yin, Tong Chen, Guanhua Ye, Wentao Zhang, Bin Cui

AI总结:

针对图压缩易受训练图结构噪声影响的问题,本文提出即插即用的RobGC,通过压缩图反馈去噪、交替优化及测试图结构校准,提升多种GC方法的鲁棒性。

摘要:

图神经网络(GNN)因其出色的图表示学习能力而受到广泛关注。然而,大规模图日益普遍,其计算需求给GNN训练带来了重大挑战,限制了GNN在多种场景中的适用性。为应对这一挑战,图压缩(GC)作为一种有前景的加速方案被提出,其重点是生成信息丰富的紧凑图,使GNN能够在保持性能的同时实现高效训练。尽管GC具有加速GNN训练的潜力,但现有GC方法在训练和推理阶段都忽视了大型训练图的质量。它们不加区分地模仿训练图分布,使压缩后的图容易受到训练图中噪声的影响,从而严重阻碍GC在复杂真实场景中的应用。为解决这一问题,我们提出了鲁棒图压缩(RobGC),这是一种面向GC的即插即用方法,用于在含噪图结构环境中扩展压缩图的鲁棒性和适用性。具体而言,RobGC利用压缩图作为反馈信号,指导原始训练图上的去噪过程。该方法为压缩和去噪过程设置了基于标签传播的交替优化策略,有助于实现压缩图与训练图的相互净化。此外,作为一种为归纳式图推理设计的GC方法,RobGC通过利用无噪声的压缩图来校准测试图的结构,从而促进测试时图去噪。大量实验表明,RobGC与多种GC方法兼容,并在不同类型和不同级别的图结构噪声下显著提升了它们的鲁棒性。

英文摘要:

Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning. However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands, limiting the applicability of GNNs in various scenarios. In response to this challenge, graph condensation (GC) is proposed as a promising acceleration solution, focusing on generating an informative compact graph that enables efficient training of GNNs while retaining performance. Despite the potential to accelerate GNN training, existing GC methods overlook the quality of large training graphs during both the training and inference stages. They indiscriminately emulate the training graph distributions, making the condensed graphs susceptible to noises within the training graph and significantly impeding the application of GC in intricate real-world scenarios. To address this issue, we propose robust graph condensation (RobGC), a plug-and-play approach for GC to extend the robustness and applicability of condensed graphs in noisy graph structure environments. Specifically, RobGC leverages the condensed graph as a feedback signal to guide the denoising process on the original training graph. A label propagation-based alternating optimization strategy is in place for the condensation and denoising processes, contributing to the mutual purification of the condensed graph and training graph. Additionally, as a GC method designed for inductive graph inference, RobGC facilitates test-time graph denoising by leveraging the noise-free condensed graph to calibrate the structure of the test graph. Extensive experiments show that RobGC is compatible with various GC methods, significantly boosting their robustness under different types and levels of graph structural noises.

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。

↑