Edge Contraction Pooling for Graph Neural Networks

Frederik Diehl

Edge Contraction Pooling for Graph Neural Networks

Machine Learning 2019-05-28 v1 Machine Learning

Authors: Frederik Diehl

Abstract

Graph Neural Network (GNN) research has concentrated on improving convolutional layers, with little attention paid to developing graph pooling layers. Yet pooling layers can enable GNNs to reason over abstracted groups of nodes instead of single nodes. To close this gap, we propose a graph pooling layer relying on the notion of edge contraction: EdgePool learns a localized and sparse hard pooling transform. We show that EdgePool outperforms alternative pooling methods, can be easily integrated into most GNN models, and improves performance on both node and graph classification.

Keywords

graph neural network graph convolutional network graph representation learning

Cite

@article{arxiv.1905.10990,
  title  = {Edge Contraction Pooling for Graph Neural Networks},
  author = {Frederik Diehl},
  journal= {arXiv preprint arXiv:1905.10990},
  year   = {2019}
}

Related papers

View all related →