Learning compact graph representations via an encoder-decoder network

Abstract Feature representation learning for classification of multiple graphs is a problem with practical applications in many domains. For instance, in chemoinformatics, the learned feature representations of molecular graphs can be used to classify molecules which exhibit anti-cancer properties....

Full description

Bibliographic Details

Published in:	Applied Network Science
Main Authors:	John Boaz Lee, Xiangnan Kong
Format:	Article
Language:	English
Published:	SpringerOpen 2019-07-01
Subjects:	Deep learning Encoder-decoder Graph classification Graph representation RNN
Online Access:	http://link.springer.com/article/10.1007/s41109-019-0157-9