Min Yimeng, Wenkel Frederik, Wolf Guy
Department of Computer Science & Operational Research, Université de Montréal.
Mila - Quebec AI Institute, Montreal, QC, Canada.
Proc IEEE Int Conf Acoust Speech Signal Process. 2021 Jun;2021:8518-8522. doi: 10.1109/icassp39728.2021.9414557. Epub 2021 May 13.
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.
几何散射最近在图表示学习中得到了认可，最近的工作表明，在图卷积网络（GCN）中集成散射特征可以缓解节点表示学习中特征典型的过平滑问题。然而，散射通常依赖于手工设计，需要通过一系列小波变换仔细选择频带，以及一种有效的权重共享方案来组合低通和带通信息。在这里，我们引入了一种新的基于注意力的架构，通过隐式学习网络中用于组合多个散射和GCN通道的节点权重，来生成自适应任务驱动的节点表示。我们表明，由此产生的几何散射注意力网络（GSAN）在半监督节点分类方面优于以前的网络，同时还通过检查节点注意力权重对提取的信息进行频谱研究。
