Affordable Access

Access to the full text

Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification

Authors
  • Shi, Shuhao
  • Qiao, Kai
  • Yang, Shuai
  • Wang, Linyuan
  • Chen, Jian
  • Yan, Bin
Type
Published Article
Journal
Frontiers in Neurorobotics
Publisher
Frontiers Media S.A.
Publication Date
Nov 25, 2021
Volume
15
Identifiers
DOI: 10.3389/fnbot.2021.775688
Source
Frontiers
Keywords
Disciplines
  • Neuroscience
  • Original Research
License
Green

Abstract

The graph neural network (GNN) has been widely used for graph data representation. However, the existing researches only consider the ideal balanced dataset, and the imbalanced dataset is rarely considered. Traditional methods such as resampling, reweighting, and synthetic samples that deal with imbalanced datasets are no longer applicable in GNN. This study proposes an ensemble model called Boosting-GNN, which uses GNNs as the base classifiers during boosting. In Boosting-GNN, higher weights are set for the training samples that are not correctly classified by the previous classifiers, thus achieving higher classification accuracy and better reliability. Besides, transfer learning is used to reduce computational cost and increase fitting ability. Experimental results indicate that the proposed Boosting-GNN model achieves better performance than graph convolutional network (GCN), GraphSAGE, graph attention network (GAT), simplifying graph convolutional networks (SGC), multi-scale graph convolution networks (N-GCN), and most advanced reweighting and resampling methods on synthetic imbalanced datasets, with an average performance improvement of 4.5%.

Report this publication

Statistics

Seen <100 times