论文标题
堆叠的图形过滤器
Stacked Graph Filter
论文作者
论文摘要
我们通过解决具有完全连接的权重与可训练的多项式系数的学习图滤波器之间的差异，从图形信号处理的角度研究图形卷积网络（GCN）。我们发现，通过使用可学习的多项式参数堆叠图形过滤器，我们可以构建一个高度适应性且健壮的顶点分类模型。我们的处理在现有顶点分类模型中放松了低频（或同等，高同性恋）的假设，从而在光谱特性方面产生了更加普遍的解决方案。从经验上讲，通过仅使用一个高参数设置，我们的模型在整个频率频谱中的大多数基准数据集上都能实现强大的结果。
We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus trainable polynomial coefficients. We find that by stacking graph filters with learnable polynomial parameters, we can build a highly adaptive and robust vertex classification model. Our treatment here relaxes the low-frequency (or equivalently, high homophily) assumptions in existing vertex classification models, resulting a more ubiquitous solution in terms of spectral properties. Empirically, by using only one hyper-parameter setting, our model achieves strong results on most benchmark datasets across the frequency spectrum.
