arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.00944cs.CVcs.AI
收藏

基于注意力的图神经网络融合潜在结构和多特征的图卷积

Attention-based Graph Convolution Fusing Latent Structures and Multiple Features for Graph Neural Networks

Tokyo University of Agriculture and Technology(东京农工大学);Osaka University(大阪大学)

Yang Li, Yuichi Tanaka

摘要:

提出了一种基于注意力的图神经网络空间图卷积算法。现有的AGC集中在只使用节点的功能,并利用一种类型的注意力函数时,计算注意力权重。相反,我们提出了两种方法来提高AGCs的表示能力,利用1)在高维空间中的结构信息和2)多个注意力函数时,计算它们的权重。第一种方法计算高维空间中图的局部结构表示。第二种方法在一个AGC中同时使用多个注意函数。这两种方法可以结合起来。我们还提出了一个GNN的分类点云和点标签的预测点云建议AGC的基础上。实验结果表明,所提方法的性能优于现有方法。我们的代码在https://github.com/liyang-tuat/SFAGC上打开。

英文摘要:

We present an attention-based spatial graph convolution (AGC) for graph neural networks (GNNs). Existing AGCs focus on only using node-wise features and utilizing one type of attention function when calculating attention weights. Instead, we propose two methods to improve the representational power of AGCs by utilizing 1) structural information in a high-dimensional space and 2) multiple attention functions when calculating their weights. The first method computes a local structure representation of a graph in a high-dimensional space. The second method utilizes multiple attention functions simultaneously in one AGC. Both approaches can be combined. We also propose a GNN for the classification of point clouds and that for the prediction of point labels in a point cloud based on the proposed AGC. According to experiments, the proposed GNNs perform better than existing methods. Our codes open at https://github.com/liyang-tuat/SFAGC.

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。

↑