论文标题
一个简单而有效的SVD-GCN，用于有向图
A Simple Yet Effective SVD-GCN for Directed Graphs
论文作者
论文摘要
在本文中，我们根据经典的单数值分解（SVD）提出了一个简单而有效的图形神经网络，称为SVD-GCN。新的图神经网络建立在图形SVD-FRAMELT上，以更好地分解SVD``频率''频段上的图形信号。此外，还通过使用Chebyshev多项式近似，将新的Framelet SVD-GCN缩放以进行更大的图形。通过在几个节点分类数据集上进行的经验实验，我们发现SVD-GCN在多种图节点学习任务上具有显着改善，并且它的表现优于GCN和许多其他用于Digraphs的先进神经网络。此外，我们从经验上说，SVD-GCN具有极大的降级能力和对高级图数据攻击的鲁棒性。理论和实验结果证明，SVD-GCN在图形数据集的一种变体中有效，同时比最新的图案保持稳定甚至更好的性能。
In this paper, we propose a simple yet effective graph neural network for directed graphs (digraph) based on the classic Singular Value Decomposition (SVD), named SVD-GCN. The new graph neural network is built upon the graph SVD-framelet to better decompose graph signals on the SVD ``frequency'' bands. Further the new framelet SVD-GCN is also scaled up for larger scale graphs via using Chebyshev polynomial approximation. Through empirical experiments conducted on several node classification datasets, we have found that SVD-GCN has remarkable improvements in a variety of graph node learning tasks and it outperforms GCN and many other state-of-the-art graph neural networks for digraphs. Moreover, we empirically demonstate that the SVD-GCN has great denoising capability and robustness to high level graph data attacks. The theoretical and experimental results prove that the SVD-GCN is effective on a variant of graph datasets, meanwhile maintaining stable and even better performance than the state-of-the-arts.
