E-GCN: graph convolution with estimated labels

Jisheng Qin, Xiaoqin Zeng, Shengli Wu, E Tang

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)
158 Downloads (Pure)


Graph Convolutional Network (GCN) has been commonly applied for semi-supervised learning tasks. How-ever, the established GCN frequently only considers the given labels in the topology optimization, which may not deliver the best performance for semi-supervised learning tasks. In this paper, we propose a novel Graph Convolutional Network with Estimated labels (E-GCN) for semi-supervised learning. The core design of E-GCN is to learn a suitable network topology for semi-supervised learning by linking both estimated labels and given labels in a centralized network frame-work. The major enhancement is that both given labels and estimated labels are utilized for the topology optimization in E-GCN, which assists the graph convolution implementation for unknown labels evaluation. Experimental results demonstrate that E-GCN is significantly better than state-of-the-art (SOTA) baselines without estimated labels.
Original languageEnglish
Pages (from-to)5007-5015
Number of pages9
JournalApplied Intelligence
Issue number7
Early online date6 Jan 2021
Publication statusPublished (in print/issue) - 31 Jul 2021

Bibliographical note

Funding Information:
This work was supported by the National Natural Science Foundation of China (No. 61170089, No. 60971088).

Publisher Copyright:
© 2021, Springer Science+Business Media, LLC, part of Springer Nature.

Copyright 2021 Elsevier B.V., All rights reserved.


  • Semi-supervised Learning, Graph Convolution Topology, Optimization Estimated Labels
  • Learning graph convolution
  • Semi-supervised
  • Topology optimization
  • Estimated labels


Dive into the research topics of 'E-GCN: graph convolution with estimated labels'. Together they form a unique fingerprint.

Cite this