论文标题
几何散射注意网络
Geometric Scattering Attention Networks
论文作者
论文摘要
几何散射最近在图表学习中获得了认可，最近的工作表明，在图形卷积网络（GCN）中整合散射特征可以减轻节点表示学习中特征的典型过度厚度。但是，散射通常依赖于手工设计，需要通过一系列小波变换来仔细选择频段，以及有效的重量共享方案，以结合低音和频道信息。在这里，我们介绍了一种新的基于注意力的体系结构，通过隐式学习节点的权重，以结合网络中的多个散射和GCN通道来产生自适应任务驱动的节点表示。我们显示所得的几何散射注意力网络（GSAN）在半监视节点分类中优于先前的网络，同时还可以通过检查节点的注意力重量来启用提取信息的光谱研究。
Geometric scattering has recently gained recognition in graph representation learning, and recent work has shown that integrating scattering features in graph convolution networks (GCNs) can alleviate the typical oversmoothing of features in node representation learning. However, scattering often relies on handcrafted design, requiring careful selection of frequency bands via a cascade of wavelet transforms, as well as an effective weight sharing scheme to combine low- and band-pass information. Here, we introduce a new attention-based architecture to produce adaptive task-driven node representations by implicitly learning node-wise weights for combining multiple scattering and GCN channels in the network. We show the resulting geometric scattering attention network (GSAN) outperforms previous networks in semi-supervised node classification, while also enabling a spectral study of extracted information by examining node-wise attention weights.
