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

Guardado en:

Detalles Bibliográficos
Autores principales:	Shuhao Shi, Kai Qiao, Shuai Yang, Linyuan Wang, Jian Chen, Bin Yan
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	graph neural network imbalanced datasets ensemble learning adaboost node classification Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/3ff80d444be64e5e98263f0fcbf7e9e3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3ff80d444be64e5e98263f0fcbf7e9e3
record_format	dspace
spelling	oai:doaj.org-article:3ff80d444be64e5e98263f0fcbf7e9e32021-11-30T22:28:55ZBoosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification1662-521810.3389/fnbot.2021.775688https://doaj.org/article/3ff80d444be64e5e98263f0fcbf7e9e32021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnbot.2021.775688/fullhttps://doaj.org/toc/1662-5218The 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 Traditional methods such as resampling, reweighting, and synthetic samples that deal with imbalanced datasets are no longer applicable in GNN.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%.Shuhao ShiKai QiaoShuai YangLinyuan WangJian ChenBin YanFrontiers Media S.A.articlegraph neural networkimbalanced datasetsensemble learningadaboostnode classificationNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neurorobotics, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	graph neural network imbalanced datasets ensemble learning adaboost node classification Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	graph neural network imbalanced datasets ensemble learning adaboost node classification Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Shuhao Shi Kai Qiao Shuai Yang Linyuan Wang Jian Chen Bin Yan Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
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	article
author	Shuhao Shi Kai Qiao Shuai Yang Linyuan Wang Jian Chen Bin Yan
author_facet	Shuhao Shi Kai Qiao Shuai Yang Linyuan Wang Jian Chen Bin Yan
author_sort	Shuhao Shi
title	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_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_sort	boosting-gnn: boosting algorithm for graph networks on imbalanced node classification
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/3ff80d444be64e5e98263f0fcbf7e9e3
work_keys_str_mv	AT shuhaoshi boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification AT kaiqiao boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification AT shuaiyang boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification AT linyuanwang boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification AT jianchen boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification AT binyan boostinggnnboostingalgorithmforgraphnetworksonimbalancednodeclassification
_version_	1718406196820443136

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

Ejemplares similares