scDEBGCL: a deep embedding approach based on bipartite graph contrastive learning for single-cell RNA-seq data [PDF]
BMC BiologyBackground Single-cell RNA sequencing (scRNA-seq) allows for the measurement of gene expression at the transcriptomic level with single-cell precision, thereby deepening our comprehension of cellular heterogeneity.
Jing Wang +5 more
doaj +2 more sources
Graph contrastive learning with node-level accurate difference [PDF]
Fundamental ResearchGraph 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 +5 more
doaj +2 more sources
A Good View for Graph Contrastive Learning [PDF]
EntropyDue to the success observed in deep neural networks with contrastive learning, there has been a notable surge in research interest in graph contrastive learning, primarily attributed to its superior performance in graphs with limited labeled data. Within
Xueyuan Chen, Shangzhe Li
doaj +2 more sources
GraphGIM: rethinking molecular graph contrastive learning via geometry image modeling [PDF]
BMC BiologyBackground 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 +6 more
doaj +2 more sources
Self-supervised Dynamic Graph Representation Learning Approach Based on Contrastive Prediction [PDF]
Jisuanji kexue, 2023 In recent years,graph self-supervised learning represented by graph contrastive learning has become a hot research to-pic in the field of graph learning.This learning paradigm does not depend on node labels and has good generalization ability.However ...
JIANG Linpu, CHEN Kejia
doaj +1 more source
Signal Contrastive Enhanced Graph Collaborative Filtering for Recommendation
Data Science and Engineering, 2023 Graph collaborative filtering methods have shown great performance improvements compared with deep neural network-based models. However, these methods suffer from data sparsity and data noise problems.
Zhi-Yuan Li +3 more
doaj +1 more source
SC-FGCL: Self-Adaptive Cluster-Based Federal Graph Contrastive Learning
IEEE Open Journal of the Computer Society, 2023 As a self-supervised learning method, the graph contrastive learning achieve admirable performance in graph pre-training tasks, and can be fine-tuned for multiple downstream tasks such as protein structure prediction, social recommendation, etc.
Tingqi Wang +4 more
doaj +1 more source
CAAI Transactions on Intelligence Technology, 2023 Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently. However, there are still two challenges.
Beibei Han +3 more
doaj +1 more source
Community-CL: An Enhanced Community Detection Algorithm Based on Contrastive Learning
Entropy, 2023 Graph contrastive learning (GCL) has gained considerable attention as a self-supervised learning technique that has been successfully employed in various applications, such as node classification, node clustering, and link prediction.
Zhaoci Huang, Wenzhe Xu, Xinjian Zhuo
doaj +1 more source
Multi-view Graph Clustering Algorithm Based on Dual Contrastive Learning and Hard Sample Mining [PDF]
Jisuanji gongchengAs a key research direction in the field of graph mining, graph clustering aims to discover substructures or node groups with similarities from graph data and classify them into the same cluster.
QIAN Lifeng, LI Jing, ZOU Xuxi, CHEN Yu, GU Yalin, WEI Xunhu
doaj +1 more source