This paper proposes a novel framework called Graph-Revised Convolutional Network (GRCN), which avoids both extremes. Specifically, a GCN-based graph revision module is introduced for predicting missing edges and revising edge weights w.r.t. downstream tasks via joint optimization. A theoretical ...
Graph convolutional networkGraph learningSemi-supervised learningGraph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linkage patterns across graphs in various applications. As real-world ...