.png){kind=icon}
返回
Dynamic graph convolutional networks by semi-supervised contrastive learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109486.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The traditional graph convolutional network(GCN) and its variants usually only propagate node informa-tion through the topology given by the dataset. However, the given topology can only represent a certain relationship and ignore some correlative feature information between nodes, which may make the graph convolutional networks unable to fully utilize the data information. To address the above issue, a novel model named Dynamic Graph Convolutional Networks by Semi-Supervised Contrastive Learning (DGSCL) is proposed in this paper. First, a feature graph is dynamically constructed from the input node features to exploit the potential correlative feature information between nodes. Then, to ensure a high-quality feature graph, a semi-supervised contrastive learning method is designed to learn discriminative node embeddings, which can iteratively refine the constructed feature graph with the learned node embed -dings. Finally, we fuse the node embeddings obtained from the given topology and the dynamic feature graph by two co-attention modules to produce more informative embeddings for the classification task. Through a series of experiments, we demonstrate the competitive performance of our model on seven node classification benchmarks.(c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Topology
Dynamic feature graph
Semi -supervised contrastive learning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
An adaptive mutual K-nearest neighbors clustering algorithm based on maximizing mutual information基于最大化互信息的自适应互K近邻聚类算法.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Interpretable learning based Dynamic Graph Convolutional Networks for Alzheimer's Disease analysis基于可解释学习的动态图卷积网络用于阿尔茨海默病分析INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏Dynamic graph structure learning for multivariate time series forecasting多变量时间序列预测的动态图结构学习PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Causal GraphSAGE: A robust graph method for classification based on causal sampling因果图: 一种基于因果抽样的鲁棒分类图方法PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
没有更多内容
没有更多内容