IEEE AccessGraph Contrastive Learning (GCL) has rapidly emerged as a key technique in self-supervised representation learning for graph-structured data. It addresses the scarcity of labeled data across domains such as recommender systems, bioinformatics, and social
Nazmul Hossain +3 more
doaj +1 more source
CLB-Defense: based on contrastive learning defense for graph neural network against backdoor attack
Tongxin xuebao, 2023 For the problem that the existing backdoor attack defense methods are difficult to deal with irregular and unstructured discrete graph data to alleviate the threat of backdoor attacks, a backdoor attack defense method for GNN based on contrastive ...
Jinyin CHEN +3 more
doaj +2 more sources
Statistical Contrastive Learning for Spatio-Temporal Anomaly Detection
Data Science in ScienceAnomaly detection is an interdisciplinary research area which attracts substantial attention both in statistics and in machine learning due to its critical role in a wide range of diverse applications, from cybersecurity to health monitoring.
Zhiwei Zhen, Yuzhou Chen, Yulia R. Gel
doaj +1 more source
Learning from Feature and Global Topologies: Adaptive Multi-View Parallel Graph Contrastive Learning
MathematicsTo address the limitations of existing graph contrastive learning methods, which fail to adaptively integrate feature and topological information and struggle to efficiently capture multi-hop information, we propose an adaptive multi-view parallel graph ...
Yumeng Song +3 more
doaj +1 more source
A multi-view contrastive learning for heterogeneous network embedding
Scientific Reports, 2023 Graph contrastive learning has been developed to learn discriminative node representations on homogeneous graphs. However, it is not clear how to augment the heterogeneous graphs without substantially altering the underlying semantics or how to design ...
Qi Li +4 more
doaj +1 more source
Multi-View Graph Contrastive Neural Networks for Session-Based Recommendation
MathematicsSession-based recommendation (SBR) aims to predict the next item a user may interact with based on an anonymous session, playing a crucial role in real-time recommendation scenarios.
Pengbo Huang, Chun Wang
doaj +1 more source
Self-Supervised Heterogeneous Graph Neural Network with Multi-scale Meta-Path Contrastive Learning
International Journal of Computational Intelligence SystemsHeterogeneous graph neural networks (HGNNs) have showcased exceptional modeling prowess in characterizing intricate structures and diverse semantic information.
Yufei Wu +3 more
doaj +1 more source
Study on Graph Collaborative Filtering Model Based on FeatureNet Contrastive Learning [PDF]
Jisuanji kexueGraph-based collaborative filtering recommendation techniques have gained significant attention for their ability to efficiently process large-scale interaction data.However,the effectiveness of these techniques is limited by the sparsity of data in real-
WU Pengyuan, FANG Wei
doaj +1 more source
Noise-augmented contrastive learning with attention for knowledge-aware collaborative recommendation
Scientific ReportsKnowledge graph (KG) plays an increasingly important role in recommender systems. Recently, Graph Convolutional Network (GCN) and Graph Attention Network (GAT) based model has gradually become the theme of Collaborative Knowledge Graph (CKG).
Wanyi Gu +4 more
doaj +1 more source
A Good View for Graph Contrastive Learning
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 +1 more source