Skip to content

Latest commit

 

History

History
18 lines (12 loc) · 492 Bytes

README.md

File metadata and controls

18 lines (12 loc) · 492 Bytes

SEGCN

Introduction

To capitalize on the information from unlabeled nodes to boost the training for GCN, we propose a novel framework named Self-Ensembling GCN (SEGCN), which marries GCN with Mean Teacher – another powerful model in semi-supervised learning.

Train and Test:

cd segcn

sh train.sh

Result will be saved in ./log.

Results