DualGCN

2018년 도입 · 논문 1편에서 사용

A dual graph convolutional neural network jointly considers the two essential assumptions of semi-supervised learning: (1) local consistency and (2) global consistency. Accordingly, two convolutional neural networks are devised to embed the local-consistency-based and global-consistency-based knowledge, respectively. Description and image from: Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification