Results 11 to 20 of about 6,810,610 (247)

Asymmetric Graph Contrastive Learning

Mathematics, 2023
Learning effective graph representations in an unsupervised manner is a popular research topic in graph data analysis. Recently, contrastive learning has shown its success in unsupervised graph representation learning.
Xinglong Chang, Jianrong Wang, Rui Guo, Yingkui Wang, Weihao Li   +4 more
doaj   +2 more sources

Molecular Graph Contrastive Learning with Line Graph [PDF]

Trapped by the label scarcity in molecular property prediction and drug design, graph contrastive learning (GCL) came forward. Leading contrastive learning works show two kinds of view generators, that is, random or learnable data corruption and domain ...
Shi, Bowen, Chen, Xueyuan, Xu, Ke, Li, Shangzhe, Liu, Ruomei, Liu, Jiaheng, Wu, Junran   +6 more
core   +9 more sources

Dual Space Graph Contrastive Learning [PDF]

, 2022
Unsupervised graph representation learning has emerged as a powerful tool to address real-world problems and achieves huge success in the graph learning domain.
Li, L, Yu, PS, Xu, G, Yang, H, Chen, H, Pan, S   +5 more
core   +1 more source

Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming [PDF]

, 2022
Graph representation learning (GRL) is critical for graph-structured data analysis. However, most of the existing graph neural networks (GNNs) heavily rely on labeling information, which is normally expensive to obtain in the real world.
Li, Ming, Zheng, Yizhen, Li, M, Li, Yuan-Fang, Li, Zhao, Jin, M, Pan, S, Peng, H, Peng, Hao, Li, YF, Jin, Ming, Li, Z, Pan, Shirui, Zheng, Y   +13 more
core   +1 more source

Prototypical Graph Contrastive Learning [PDF]

, 2022
Graph-level representations are critical in various real-world applications, such as predicting the properties of molecules. But in practice, precise graph annotations are generally very expensive and time-consuming.
Zhao, Ruihui, Eric Xing, Chen Liu, Xing, Eric, Zhou, Pan, Shuojia Wang, LIU, Chen, Hu, Zi-Yuan, Pan Zhou, Wang, Shuojia, Zheng, Yefeng, Lin, Shuai, Xiaodan Liang, Lin, Liang, Zi-Yuan Hu, Ruihui Zhao, Yefeng Zheng, Liang Lin, Shuai Lin, Liang, Xiaodan   +19 more
core   +1 more source

Boosting Graph Contrastive Learning via Adaptive Sampling

, 2023
Contrastive learning (CL) is a prominent technique for self-supervised representation learning, which aims to contrast semantically similar (i.e., positive) and dissimilar (i.e., negative) pairs of examples under different augmented views.
Chen Gong, Tao, Dacheng, Wan, Sheng, Yibing Zhan, Gong, Chen, Shuo Chen, Shirui Pan, Jian Yang, Dacheng Tao, Yang, Jian, Zhan, Yibing, Chen, Shuo, Pan, Shirui, Sheng Wan   +13 more
core   +1 more source

Contrastive and attentive graph learning for multi-view clustering

, 2022
Graph-based multi-view clustering aims to take advantage of multiple view graph information to provide clustering solutions. The consistency constraint of multiple views is the key of multi-view graph clustering.
Li, Lin, Liu, Peiyu, Tao, Xiaohui, Wang, Peipei, Wang, Ru   +4 more
core   +1 more source

Attraction and Repulsion: Unsupervised Domain Adaptive Graph Contrastive Learning Network

, 2022
Graph convolutional networks (GCNs) are important techniques for analytics tasks related to graph data. To date, most GCNs are designed for a single graph domain. They are incapable of transferring knowledge from/to different domains (graphs), due to the
Wu, M, Wu, Man, Pan, Shirui, Zhu, X, Pan, S, Zhu, Xingquan   +5 more
core   +1 more source

Neighbor Contrastive Learning on Learnable Graph Augmentation

, 2023
Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly adopt human-designed graph augmentations, which are sensitive to various graph ...
Sun, D, Yang, LT, Shen, X, Zhou, X, Pan, S   +4 more
core   +1 more source

XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

, 2023
Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance. The underlying principle of CL-based recommendation models is to ensure the consistency between representations derived from different graph ...
Tong Chen, Xin Xia, Nguyen Quoc Viet Hung, Cui, L, Junliang Yu, Lizhen Cui, Yu, J, Chen, T, Xia, X, Hongzhi Yin, Hung, NQV, Yin, H   +11 more
core   +1 more source