User: Guest  Login
Document type:
Zeitschriftenaufsatz
Author(s):
Diehl, Frederik
Title:
Edge Contraction Pooling for Graph Neural Networks
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 i...     »
Journal title:
CoRR
Year:
2019
Journal volume:
abs/1905.10990
WWW:
http://arxiv.org/abs/1905.10990
 BibTeX