arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.12386cs.LGstat.ML
收藏

定制图神经网络

Customized Graph Neural Networks

Michigan State University(密歇根州立大学);Microsoft Research Asia(微软亚洲研究院);IBM T. J. Watson Research Center(IBM托马斯·J·沃森研究中心)

Yiqi Wang, Yao Ma, Wei Jin, Chaozhuo Li, Charu Aggarwal, Jiliang Tang

摘要:

最近,图神经网络(GNNs)大大推进了图分类的任务。通常,我们首先在给定的训练集中构建一个统一的GNN模型,然后使用这个统一的模型来预测测试集中所有未见过的图的标签。然而,同一数据集中的图通常具有显著不同的结构,这表明统一模型在给定单个图的情况下可能是次优的。因此,在本文中,我们的目标是开发定制的图神经网络的图形分类。具体来说,我们提出了一种新的定制图神经网络框架,即,自定义GNN。给定一个图样本,Customized-GNN可以基于其结构为该图生成一个特定于样本的模型。同时,该框架具有很强的通用性,可以应用于现有的众多图神经网络模型。各种图分类基准上的综合实验证明了所提出的框架的有效性。

英文摘要:

Recently, Graph Neural Networks (GNNs) have greatly advanced the task of graph classification. Typically, we first build a unified GNN model with graphs in a given training set and then use this unified model to predict labels of all the unseen graphs in the test set. However, graphs in the same dataset often have dramatically distinct structures, which indicates that a unified model may be sub-optimal given an individual graph. Therefore, in this paper, we aim to develop customized graph neural networks for graph classification. Specifically, we propose a novel customized graph neural network framework, i.e., Customized-GNN. Given a graph sample, Customized-GNN can generate a sample-specific model for this graph based on its structure. Meanwhile, the proposed framework is very general that can be applied to numerous existing graph neural network models. Comprehensive experiments on various graph classification benchmarks demonstrate the effectiveness of the proposed 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。

↑