Interpreting and Understanding Graph Convolutional Neural Network using Gradient-based Attribution Method

no code implementations • 9 Mar 2019 • Shangsheng Xie, Mingming Lu

To solve the problem that convolutional neural networks (CNNs) are difficult to process non-grid type relational data like graphs, Kipf et al. proposed a graph convolutional neural network (GCN).

Few-Shot Learning Node Classification