CSC-GCN: Contrastive semantic calibration for graph convolution network

Graph convolutional networks (GCNs) have been successfully applied to node representation learning in various real-world applications. However, the performance of GCNs drops rapidly when the labeled data are severely scarce, and the node features are prone to being indistinguishable with stacking mo...

Full description

Saved in:
Bibliographic Details
Main Authors: Xu Yang, Kun Wei, Cheng Deng
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2023-11-01
Series:Journal of Information and Intelligence
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949715923000598
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417304124686336
author Xu Yang
Kun Wei
Cheng Deng
author_facet Xu Yang
Kun Wei
Cheng Deng
author_sort Xu Yang
collection DOAJ
description Graph convolutional networks (GCNs) have been successfully applied to node representation learning in various real-world applications. However, the performance of GCNs drops rapidly when the labeled data are severely scarce, and the node features are prone to being indistinguishable with stacking more layers, causing over-fitting and over-smoothing problems. In this paper, we propose a simple yet effective contrastive semantic calibration for graph convolution network (CSC-GCN), which integrates stochastic identity aggregation and semantic calibration to overcome these weaknesses. The basic idea is the node features obtained from different aggregation operations should be similar. Toward that end, identity aggregation is utilized to extract semantic features from labeled nodes, while stochastic label noise is adopted to alleviate the over-fitting problem. Then, contrastive learning is employed to improve the discriminative ability of the node features, and the features from different aggregation operations are calibrated according to the class center similarity. In this way, the similarity between unlabeled features and labeled ones from the same class is enhanced while effectively reducing the over-smoothing problem. Experimental results on eight popular datasets show that the proposed CSC-GCN outperforms state-of-the-art methods on various classification tasks.
format Article
id doaj-art-042ccebc4ae44243944d0ea4681692b3
institution Kabale University
issn 2949-7159
language English
publishDate 2023-11-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Journal of Information and Intelligence
spelling doaj-art-042ccebc4ae44243944d0ea4681692b32025-08-20T03:32:54ZengKeAi Communications Co., Ltd.Journal of Information and Intelligence2949-71592023-11-011429530710.1016/j.jiixd.2023.10.001CSC-GCN: Contrastive semantic calibration for graph convolution networkXu Yang0Kun Wei1Cheng Deng2School of Electronic Engineering, Xidian University, Xi'an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi'an 710071, ChinaCorresponding author.; School of Electronic Engineering, Xidian University, Xi'an 710071, ChinaGraph convolutional networks (GCNs) have been successfully applied to node representation learning in various real-world applications. However, the performance of GCNs drops rapidly when the labeled data are severely scarce, and the node features are prone to being indistinguishable with stacking more layers, causing over-fitting and over-smoothing problems. In this paper, we propose a simple yet effective contrastive semantic calibration for graph convolution network (CSC-GCN), which integrates stochastic identity aggregation and semantic calibration to overcome these weaknesses. The basic idea is the node features obtained from different aggregation operations should be similar. Toward that end, identity aggregation is utilized to extract semantic features from labeled nodes, while stochastic label noise is adopted to alleviate the over-fitting problem. Then, contrastive learning is employed to improve the discriminative ability of the node features, and the features from different aggregation operations are calibrated according to the class center similarity. In this way, the similarity between unlabeled features and labeled ones from the same class is enhanced while effectively reducing the over-smoothing problem. Experimental results on eight popular datasets show that the proposed CSC-GCN outperforms state-of-the-art methods on various classification tasks.http://www.sciencedirect.com/science/article/pii/S2949715923000598Graph convolution networkContrastive learningSemi-supervised learning
spellingShingle Xu Yang
Kun Wei
Cheng Deng
CSC-GCN: Contrastive semantic calibration for graph convolution network
Journal of Information and Intelligence
Graph convolution network
Contrastive learning
Semi-supervised learning
title CSC-GCN: Contrastive semantic calibration for graph convolution network
title_full CSC-GCN: Contrastive semantic calibration for graph convolution network
title_fullStr CSC-GCN: Contrastive semantic calibration for graph convolution network
title_full_unstemmed CSC-GCN: Contrastive semantic calibration for graph convolution network
title_short CSC-GCN: Contrastive semantic calibration for graph convolution network
title_sort csc gcn contrastive semantic calibration for graph convolution network
topic Graph convolution network
Contrastive learning
Semi-supervised learning
url http://www.sciencedirect.com/science/article/pii/S2949715923000598
work_keys_str_mv AT xuyang cscgcncontrastivesemanticcalibrationforgraphconvolutionnetwork
AT kunwei cscgcncontrastivesemanticcalibrationforgraphconvolutionnetwork
AT chengdeng cscgcncontrastivesemanticcalibrationforgraphconvolutionnetwork