arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.14951cs.LGcs.AIcs.SI
收藏

简单图压缩

Simple Graph Condensation

Zhejiang University(浙江大学);Hangzhou City University(杭州城市大学)

Zhenbang Xiao, Yu Wang, Shunyu Liu, Huiqiong Wang, Mingli Song, Tongya Zheng

AI总结:

提出SimGC框架,通过预训练SGC模型从输入层到预测层对齐压缩图与原始图,消除外部参数,实现高达10倍加速且性能与最先进方法相当。

摘要:

大规模图上的繁重训练成本引起了人们对图压缩的极大兴趣,图压缩涉及在一个小型压缩图上调整图神经网络(GNNs),以便用于大规模原始图。现有方法主要侧重于对齐压缩图与原始图之间的关键指标,如梯度、输出分布和GNNs的轨迹,在下游任务上取得了令人满意的性能。然而,这些复杂指标需要复杂的外部参数,并可能破坏压缩图的优化过程,使得压缩过程要求极高且不稳定。受近期简化模型在各个领域取得成功的启发,我们提出了一种简化的图压缩指标对齐方法,旨在减少从复杂指标中继承的不必要复杂性。我们引入了简单图压缩(SimGC)框架,该框架在预训练于原始图上的简单图卷积(SGC)模型的指导下,从输入层到预测层将压缩图与原始图对齐。重要的是,SimGC消除了外部参数,并在压缩过程中仅保留目标压缩图。这种简单而有效的策略相比现有图压缩方法实现了高达10倍的显著加速,同时与最先进的基线性能相当。在七个基准数据集上进行的全面实验证明了SimGC在预测准确性、压缩时间和泛化能力方面的有效性。我们的代码可在https://github.com/BangHonor/SimGC获取。

英文摘要:

The burdensome training costs on large-scale graphs have aroused significant interest in graph condensation, which involves tuning Graph Neural Networks (GNNs) on a small condensed graph for use on the large-scale original graph. Existing methods primarily focus on aligning key metrics between the condensed and original graphs, such as gradients, output distribution and trajectories of GNNs, yielding satisfactory performance on downstream tasks. However, these complex metrics necessitate intricate external parameters and can potentially disrupt the optimization process of the condensation graph, making the condensation process highly demanding and unstable. Motivated by the recent success of simplified models across various domains, we propose a simplified approach to metric alignment in graph condensation, aiming to reduce unnecessary complexity inherited from intricate metrics. We introduce the Simple Graph Condensation (SimGC) framework, which aligns the condensed graph with the original graph from the input layer to the prediction layer, guided by a pre-trained Simple Graph Convolution (SGC) model on the original graph. Importantly, SimGC eliminates external parameters and exclusively retains the target condensed graph during the condensation process. This straightforward yet effective strategy achieves a significant speedup of up to 10 times compared to existing graph condensation methods while performing on par with state-of-the-art baselines. Comprehensive experiments conducted on seven benchmark datasets demonstrate the effectiveness of SimGC in prediction accuracy, condensation time, and generalization capability. Our code is available at https://github.com/BangHonor/SimGC.

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。

↑