通过自表达图结构重建的图数据压缩
Graph Data Condensation via Self-expressive Graph Structure Reconstruction
AI总结:
本文提出GCSR框架,通过将原始图结构显式融入压缩过程并重建可解释的自表达图结构,解决现有图数据压缩方法忽视结构信息和可解释性不足的问题,实验证明其在多种GNN模型和数据集上有效。
摘要:
随着在大规模图上训练图神经网络(GNN)的需求日益增长,图数据压缩已成为缓解训练阶段存储和时间成本的关键技术。其目标是将原始大规模图压缩为一个规模小得多的合成图,同时保留高效训练下游GNN所必需的关键信息。然而,现有方法要么只专注于优化节点特征,要么试图独立地学习节点特征和图结构生成器。它们无法明确利用原始图结构的信息,也未能为合成数据集构建可解释的图结构。为了解决这些问题,我们提出了一种新颖的框架,名为通过自表达图结构重建的图数据压缩(GCSR)。我们的方法突出之处在于:(1)明确地将原始图结构纳入压缩过程;(2)通过重建可解释的自表达图结构来捕捉压缩节点之间细微的相互依赖关系。大量实验和全面分析验证了所提方法在多种GNN模型和数据集上的有效性。我们的代码可在 https://github.com/zclzcl0223/GCSR 获取。
英文摘要:
With the increasing demands of training graph neural networks (GNNs) on large-scale graphs, graph data condensation has emerged as a critical technique to relieve the storage and time costs during the training phase. It aims to condense the original large-scale graph to a much smaller synthetic graph while preserving the essential information necessary for efficiently training a downstream GNN. However, existing methods concentrate either on optimizing node features exclusively or endeavor to independently learn node features and the graph structure generator. They could not explicitly leverage the information of the original graph structure and failed to construct an interpretable graph structure for the synthetic dataset. To address these issues, we introduce a novel framework named \textbf{G}raph Data \textbf{C}ondensation via \textbf{S}elf-expressive Graph Structure \textbf{R}econstruction (\textbf{GCSR}). Our method stands out by (1) explicitly incorporating the original graph structure into the condensing process and (2) capturing the nuanced interdependencies between the condensed nodes by reconstructing an interpretable self-expressive graph structure. Extensive experiments and comprehensive analysis validate the efficacy of the proposed method across diverse GNN models and datasets. Our code is available at \url{https://github.com/zclzcl0223/GCSR}.
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。