Benutzer: Gast  Login
Dokumenttyp:
Konferenzbeitrag 
Art des Konferenzbeitrags:
Poster 
Autor(en):
Frederik Diehl, Thomas Brunner, Michael Truong Le and Alois Knoll 
Titel:
Towards Graph Pooling by Edge Contraction 
Abstract:
Graph Neural Networks (GNNs) research has concentrated on improving convolutional layers, with little attention paid to developing graph poolinglayers. Yet pooling layers can enable GNNs toreason over abstracted groups of nodes instead ofsingle nodes, thus increasing their generalization potential. To close this gap, we propose a graph pooling layer relying on the notion of edge con-traction: EdgePool learns a localized and sparse pooling transform. We evaluate it on four datasets, finding that...    »
 
Kongress- / Buchtitel:
ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data 
Publikationsdatum:
15.06.2019 
Jahr:
2019