Graph Convolution Network

数学上卷积的定义是：

\[ s(t) = \int x(a) w(t-a) da \]

卷积操作常用\(s(t) = (x * w)(t)\)表示

在卷积神经网络中，the first argument \(x\) is often referred to as the input and the second argument as the kernel. The output is sometimes referred to as feature.