论文标题
基于磁帧的卷积神经网络，用于有向图
A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs
论文作者
论文摘要
光谱图卷积网络（Spectral GCNNS）是一种用于分析和处理图数据的强大工具，通常通过傅立叶变换应用频率过滤，以获取具有选择性信息的表示形式。尽管研究表明，基于帧的过滤可以增强光谱GCNN，但大多数此类研究仅考虑了无方向的图。在本文中，我们介绍了Framelet-Magnet，这是一种用于有向图的基于磁帧的光谱GCNN（Digraphs）。该模型将帧转换应用于Digraph信号，形成更复杂的表示进行过滤。 Digraph Framelets是用复合值磁拉曲板构建的，同时导致了真实和复杂域中的信号处理。我们从经验上验证了在节点分类，链接预测和denoising中的一系列最新模型上，帧量器的预测能力。
Spectral Graph Convolutional Networks (spectral GCNNs), a powerful tool for analyzing and processing graph data, typically apply frequency filtering via Fourier transform to obtain representations with selective information. Although research shows that spectral GCNNs can be enhanced by framelet-based filtering, the massive majority of such research only considers undirected graphs. In this paper, we introduce Framelet-MagNet, a magnetic framelet-based spectral GCNN for directed graphs (digraphs). The model applies the framelet transform to digraph signals to form a more sophisticated representation for filtering. Digraph framelets are constructed with the complex-valued magnetic Laplacian, simultaneously leading to signal processing in both real and complex domains. We empirically validate the predictive power of Framelet-MagNet over a range of state-of-the-art models in node classification, link prediction, and denoising.
