Cargando…

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

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 imb...

Descripción completa

Detalles Bibliográficos
Autores principales: Shi, Shuhao, Qiao, Kai, Yang, Shuai, Wang, Linyuan, Chen, Jian, Yan, Bin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8655128/
https://www.ncbi.nlm.nih.gov/pubmed/34899230
http://dx.doi.org/10.3389/fnbot.2021.775688
_version_ 1784612017182605312
author Shi, Shuhao
Qiao, Kai
Yang, Shuai
Wang, Linyuan
Chen, Jian
Yan, Bin
author_facet Shi, Shuhao
Qiao, Kai
Yang, Shuai
Wang, Linyuan
Chen, Jian
Yan, Bin
author_sort Shi, Shuhao
collection PubMed
description 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 Traditional methods such as resampling, reweighting, and synthetic samples that deal with imbalanced datasets are no longer applicable in GNN.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%.
format Online
Article
Text
id pubmed-8655128
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-86551282021-12-10 Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification Shi, Shuhao Qiao, Kai Yang, Shuai Wang, Linyuan Chen, Jian Yan, Bin Front Neurorobot Neuroscience 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%. Frontiers Media S.A. 2021-11-25 /pmc/articles/PMC8655128/ /pubmed/34899230 http://dx.doi.org/10.3389/fnbot.2021.775688 Text en Copyright © 2021 Shi, Qiao, Yang, Wang, Chen and Yan. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Shi, Shuhao
Qiao, Kai
Yang, Shuai
Wang, Linyuan
Chen, Jian
Yan, Bin
Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
title Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
title_full Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
title_fullStr Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
title_full_unstemmed Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
title_short Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
title_sort boosting-gnn: boosting algorithm for graph networks on imbalanced node classification
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8655128/
https://www.ncbi.nlm.nih.gov/pubmed/34899230
http://dx.doi.org/10.3389/fnbot.2021.775688
work_keys_str_mv AT shishuhao boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification
AT qiaokai boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification
AT yangshuai boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification
AT wanglinyuan boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification
AT chenjian boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification
AT yanbin boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification