Dissecting Graph Neural Networks on Graph Classification
arXiv: Learning, 2019.
Graph Neural Nets (GNNs) have received increasing attentions, partially due to their superior performance in many node and graph classification tasks. However, there is a lack of understanding on what they are learning and how sophisticated the learned graph functions are. In this work, we first propose Graph Feature Network (GFN), a si...More
PPT (Upload PPT)