Self-supervised Training of Graph Convolutional Networks

06/03/2020
by   Qikui Zhu, et al.
58

Graph Convolutional Networks (GCNs) have been successfully applied to analyze non-grid data, where the classical convolutional neural networks (CNNs) cannot be directly used. One similarity shared by GCNs and CNNs is the requirement of massive amount of labeled data for network training. In addition, GCNs need the adjacency matrix as input to define the relationship between those non-grid data, which leads to all of data including training, validation and test data typically forms only one graph structures data for training. Furthermore, the adjacency matrix is usually pre-defined and stationary, which makes the data augmentation strategies cannot be employed on the constructed graph structures data to augment the amount of training data. To further improve the learning capacity and model performance under the limited training data, in this paper, we propose two types of self-supervised learning strategies to exploit available information from the input graph structure data itself. Our proposed self-supervised learning strategies are examined on two representative GCN models with three public citation network datasets - Citeseer, Cora and Pubmed. The experimental results demonstrate the generalization ability as well as the portability of our proposed strategies, which can significantly improve the performance of GCNs with the power of self-supervised learning in improving feature learning.

READ FULL TEXT

page 1

page 5

research
02/28/2019

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks

Graph Convolutional Networks(GCNs) play a crucial role in graph learning...
research
05/25/2021

Graph Self Supervised Learning: the BT, the HSIC, and the VICReg

Self-supervised learning and pre-training strategies have developed over...
research
08/17/2021

RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks

To further improve the performance and the self-learning ability of GCNs...
research
08/06/2020

Graph Convolutional Networks for Hyperspectral Image Classification

Convolutional neural networks (CNNs) have been attracting increasing att...
research
06/18/2020

UV-Net: Learning from Curve-Networks and Solids

Parametric curves, surfaces and boundary representations are the basis f...
research
07/13/2021

A Graph Data Augmentation Strategy with Entropy Preserving

The Graph Convolutional Networks (GCNs) proposed by Kipf and Welling are...

Please sign up or login with your details

Forgot password? Click here to reset