Hierarchical Graph Pooling with Structure Learning

Understand

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks.

• However, existing GNN models mainly focus on designing graph convolution operations.
• The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked.
• In this paper, we propose a novel graph pooling operator, called Hierarchical Graph Pooling with Structure Learning (HGP-SL), which can be integrated into various graph neural network architectures.