Results 31 to 40 of about 533 (49)

Graph contrastive learning with node-level accurate difference

Fundamental Research
Graph contrastive learning (GCL) has attracted extensive research interest due to its powerful ability to capture latent structural and semantic information of graphs in a self-supervised manner.
Pengfei Jiao, Kaiyan Yu, Qing Bao, Ying Jiang, Xuan Guo, Zhidong Zhao   +5 more
doaj   +1 more source

Prototype based contrastive graph clustering network for reducing false negatives

Scientific Reports
Contrastive graph clustering methods significantly enhance the clustering performance of graph data by leveraging multi-view augmentation and contrastive loss. In particular, Self-Supervised Graph Contrastive Learning (SS-GCL) has gained attention due to
Cuihua Ma, Chaosheng Tang, Ziqi Deng, Fuyun Li, Haixia Long, Jieren Cheng   +5 more
doaj   +1 more source

Node classification in complex networks based on multi-view debiased contrastive learning

Complex & Intelligent Systems
In complex networks, contrastive learning has emerged as a crucial technique for acquiring discriminative representations from graph data. Maximizing the similarity among relevant sample pairs while minimizing that among irrelevant pairs is pivotal in ...
Zhe Li, Lei Zhou, Yandong Hou, Min Ji, Zhuanzheng Hang, Bolun Chen   +5 more
doaj   +1 more source

Multi-view Contrastive Recommendation Algorithm Based on Adaptive Enhancement [PDF]

Jisuanji gongcheng
Recommendation systems based on neural network architectures have achieved remarkable success in recent years; however, they fail to achieve the desired results when dealing with data rich in popularity biases and interaction noise. Contrastive learning,
YAO Xun, WANG Haipeng, HU Xinrong, YANG Jie
doaj   +1 more source

Rethinking spatial-temporal contrastive learning for Urban traffic flow forecasting: multi-level augmentation framework

Complex & Intelligent Systems
Graph neural networks integrating contrastive learning have attracted growing attention in urban traffic flow forecasting. However, most existing graph contrastive learning methods do not perform well in capturing local–global spatial dependencies or ...
Lin Pan, Qianqian Ren, Zilong Li, Xingfeng Lv   +3 more
doaj   +1 more source

Knowledge Graph Completion Algorithm with Multi-view Contrastive Learning [PDF]

Jisuanji kexue yu tansuo
Knowledge graph completion is a process of reasoning new triples based on existing entities and relations in knowledge graph. The existing methods usually use the encoder-decoder framework.
QIAO Zifeng, QIN Hongchao, HU Jingjing, LI Ronghua, WANG Guoren
doaj   +1 more source

Contrastive learning for traffic flow forecasting based on multi graph convolution network

IET Intelligent Transport Systems
Contrastive learning is an increasingly important research direction and has attracted considerable attention in the field of computer vision. It can greatly improve the representativeness of image features through data augmentation, unsupervised ...
Kan Guo, Daxin Tian, Yongli Hu, Yanfeng Sun, Zhen (Sean) Qian, Jianshan Zhou, Junbin Gao, Baocai Yin   +7 more
doaj   +1 more source

Cross-View Negative-Free Contrastive Learning for Graph Anomaly Detection with High-Order Structure Augmentation [PDF]

Jisuanji kexue yu tansuo
Graph anomaly detection has practical applications in various fields, such as cyber security, financial evaluation and medical care. Recently, contrastive-based and generative-based detection frameworks have achieved remarkable performance improvements ...
JIN Hu, HU Jingtao, WANG Siwei, ZHU En, LUO Lei, DUAN Jingcan
doaj   +1 more source

GraphGIM: rethinking molecular graph contrastive learning via geometry image modeling

BMC Biology
Background Learning molecular representations is crucial for accurate drug discovery. Using graphs to represent molecules is a popular solution, and many researchers have used contrastive learning to improve the generalization of molecular graph ...
Chaoyi Li, Hongxin Xiang, Wenjie Du, Tengfei Ma, Haowen Chen, Xiangxiang Zeng, Lei Xu   +6 more
doaj   +1 more source

Beyond contrastive learning: adaptive graph representations with mutual information maximization for blockchain and structured data

Complex & Intelligent Systems
Graph representation learning has emerged as a powerful approach for modeling structured data across diverse domains, including social networks, biochemical interactions, and financial transaction systems.
Yifeng Zhang, Qianqian Ren, Yourong Chen, Meng Han   +3 more
doaj   +1 more source