DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

ICLR, 2020.

Cited by: 14|Views805
EI
Weibo:
We have presented DropEdge, a novel and efficient technique to facilitate the development of deep Graph Convolutional Networks

Abstract:

Over-fitting and over-smoothing are two main obstacles of developing deep Graph Convolutional Networks (GCNs) for node classification. In particular, over-fitting weakens the generalization ability on small dataset, while over-smoothing impedes model training by isolating output representations from the input features with the increase in...More
0
Your rating :
0

 

Tags
Comments