Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
arXiv:2105.11625 · doi:10.3389/fnbot.2021.775688
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 Traditional methods such as resampling, reweighting, and synthetic samples that deal with imbalanced datasets are no longer applicable in GNN.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 paper 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 classifier, 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 GCN, GraphSAGE, GAT, SGC, N-GCN, and most advanced reweighting and resampling methods on synthetic imbalanced datasets, with an average performance improvement of 4.5%
arXiv comment19 pages, 6 figures published on Frontiers in Neurorobotics
References in corpus (7)
- SMOTE: Synthetic Minority Over-sampling Technique
- A systematic study of the class imbalance problem in convolutional neural networks
- Simplifying Graph Convolutional Networks
- Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
- Predicting multicellular function through multi-layer tissue networks
- What is the Effect of Importance Weighting in Deep Learning?
- RPC: A Large-Scale Retail Product Checkout Dataset