Results 11 to 20 of about 30,335 (256)
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 +4 more
doaj +2 more sources
ArieL: Adversarial Graph Contrastive Learning. [PDF]
ACM Trans Knowl Discov Data, 2023 Contrastive learning is an effective unsupervised method in graph representation learning. The key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of nodes in the graph as the principle.
Feng S, Jing B, Zhu Y, Tong H.
europepmc +4 more sources
Graph contrastive learning with implicit augmentations
Neural Networks, 2023 Existing graph contrastive learning methods rely on augmentation techniques based on random perturbations (e.g., randomly adding or dropping edges and nodes). Nevertheless, altering certain edges or nodes can unexpectedly change the graph characteristics, and choosing the optimal perturbing ratio for each dataset requires onerous manual tuning. In this
Huidong Liang +5 more
openaire +3 more sources
Graph Communal Contrastive Learning
Proceedings of the ACM Web Conference 2022, 2022 Graph representation learning is crucial for many real-world applications (e.g. social relation analysis). A fundamental problem for graph representation learning is how to effectively learn representations without human labeling, which is usually costly and time-consuming. Graph contrastive learning (GCL) addresses this problem by pulling the positive
Li, Bolian, Jing, Baoyu, Tong, Hanghang
openaire +2 more sources
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
CCGL: Contrastive Cascade Graph Learning [PDF]
IEEE Transactions on Knowledge and Data Engineering, 2022 IEEE TKDE, including 15 pages, 7 figures, and 12 ...
Xu, Xovee +3 more
openaire +2 more sources
Bayesian Graph Contrastive Learning
, 2021 Contrastive learning has become a key component of self-supervised learning approaches for graph-structured data. Despite their success, existing graph contrastive learning methods are incapable of uncertainty quantification for node representations or their downstream tasks, limiting their application in high-stakes domains.
Hasanzadeh, Arman +5 more
openaire +2 more sources
Generative-Contrastive Graph Learning for Recommendation
Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023 By treating users' interactions as a user-item graph, graph learning models have been widely deployed in Collaborative Filtering(CF) based recommendation. Recently, researchers have introduced Graph Contrastive Learning(GCL) techniques into CF to alleviate the sparse supervision issue, which first constructs contrastive views by data augmentations and ...
Yonghui Yang +7 more
openaire +2 more sources
Local structure-aware graph contrastive representation learning
Neural Networks, 2023 Traditional Graph Neural Network (GNN), as a graph representation learning method, is constrained by label information. However, Graph Contrastive Learning (GCL) methods, which tackle the label problem effectively, mainly focus on the feature information of the global graph or small subgraph structure (e.g., the first-order neighborhood). In the paper,
Yang, Kai +4 more
openaire +3 more sources
Prototypical Graph Contrastive Learning
, 2021 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. To address this issue, graph contrastive learning constructs instance discrimination task which pulls together positive pairs ...
Lin, Shuai +8 more
openaire +2 more sources