arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.13697cs.LGcs.AI
收藏

基于感受野分布匹配的图压缩

Graph Condensation via Receptive Field Distribution Matching

Georgia Institute of Technology(佐治亚理工学院)

Mengyang Liu, Shanchuan Li, Xinshi Chen, Le Song

摘要:

图神经网络(GNN)能够使用深度学习来分析图,在捕获图中的结构化信息方面具有很好的效果。本文的重点是创建一个小图来表示原始图,以便在缩小的图上训练的GNN可以做出准确的预测。我们将原始图视为感受野的分布,并旨在合成一个感受野具有相似分布的小图。因此,我们提出了通过接受场分布匹配(GCDM),这是通过优化合成图,通过使用最大平均差异(MMD)量化的分布匹配损失来完成的图形Condesation。此外,我们证明了GCDM生成的合成图是高度概括的各种模型在评估阶段,冷凝速度显着提高使用这个框架。

英文摘要:

Graph neural networks (GNNs) enable the analysis of graphs using deep learning, with promising results in capturing structured information in graphs. This paper focuses on creating a small graph to represent the original graph, so that GNNs trained on the size-reduced graph can make accurate predictions. We view the original graph as a distribution of receptive fields and aim to synthesize a small graph whose receptive fields share a similar distribution. Thus, we propose Graph Condesation via Receptive Field Distribution Matching (GCDM), which is accomplished by optimizing the synthetic graph through the use of a distribution matching loss quantified by maximum mean discrepancy (MMD). Additionally, we demonstrate that the synthetic graph generated by GCDM is highly generalizable to a variety of models in evaluation phase and that the condensing speed is significantly improved using this framework.

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。

↑