← Search

Charles E. Martin

2 accepted papers

2019

Explainability Methods for Graph Convolutional Neural Networks

CVPR 2019oral

With the growing use of graph convolutional neural networks (GCNNs) comes the need for explainability. In this paper, we introduce explainability methods for GCNNs. We develop the graph analogues of three prominent explainability methods for convolutional neural networks: contrastive gradient-based…

Cited by 716PDFScholar