Results 21 to 30 of about 6,810,610 (247)

Unifying Graph Contrastive Learning with Flexible Contextual Scopes

, 2022
Graph contrastive learning (GCL) has recently emerged as an effective learning paradigm to alleviate the reliance on labelling information for graph representation learning. The core of GCL is to maximise the mutual information between the representation
Zhou, X, Lee, VC, Zheng, Y, Gong, C, Pan, S   +4 more
core   +1 more source

Adversarial Graph Contrastive Learning with Information Regularization [PDF]

, 2023
Contrastive learning is an effective unsupervised method in graph representation learning. Recently, the data augmentation based contrastive learning method has been extended from images to graphs.
Tong, Hanghang, Zhu, Yada, Jing, Baoyu, Feng, Shengyu   +3 more
core   +1 more source

Are Graph Augmentations Necessary?: Simple Graph Contrastive Learning for Recommendation

, 2022
Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling the data ...
Cui, Lizhen, Yu, Junliang, Nguyen, Quoc Viet Hung, Yin, Hongzhi, Xia, Xin, Chen, Tong   +5 more
core   +1 more source

XSGCL: A Lightweight Graph Contrastive Learning Framework for Recommendation [PDF]

Jisuanji gongcheng
Traditional recommendation models based on contrastive learning first perform data augmentation on the original interaction graph and then strive to improve the consistency of representations encoded from different views.
ZHANG Zhen, YOU Lan, PENG Qingxi, JIN Hong, ZENG Haoqiu, XIA Yuchun
doaj   +1 more source

Subgraph Adaptive Structure-Aware Graph Contrastive Learning

Mathematics, 2022
Graph contrastive learning (GCL) has been subject to more attention and been widely applied to numerous graph learning tasks such as node classification and link prediction. Although it has achieved great success and even performed better than supervised
Zhikui Chen, Yin Peng, Shuo Yu, Chen Cao, Feng Xia   +4 more
doaj   +1 more source

LinkFND: Simple Framework for False Negative Detection in Recommendation Tasks With Graph Contrastive Learning

IEEE Access, 2023
Self-supervised learning has been shown to be effective in various fields, proving its usefulness in contrastive learning. Recently, graph contrastive learning has shown state-of-the-art performance in the recommendation task.
Sanghun Kim, Hyeryung Jang
doaj   +1 more source

Adversarial graph contrastive learning with information regularization [PDF]

, 2022
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo termsThe student, Shengyu Feng, accepted the attached license on 2022-04-24 at 01:50.The student, Shengyu Feng ...
Feng, Shengyu
core  

Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection

, 2023
Anomaly detection from graph data has drawn much attention due to its practical significance in many critical applications including cybersecurity, finance, and social networks. Existing data mining and machine learning methods are either shallow methods
Zheng, Yu, Jin, Ming, Chen, Yi-Ping Phoebe, Phan, Khoa T, Liu, Yixin, Chi, Lianhua   +5 more
core   +1 more source

CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning

, 2022
Graph similarity learning refers to calculating the similarity score between two graphs, which is required in many realistic applications, such as visual tracking, graph classification, and collaborative filtering.
Jin, D, Wei Lin, Xiang Li, Pan, S, Shirui Pan, Di Jin, Wang, L, Luzhi Wang, Yizhen Zheng, Li, X, Lin, W, Zheng, Y, Fei Jiang, Jiang, F   +13 more
core   +1 more source

CC-GNN: A Clustering Contrastive Learning Network for Graph Semi-Supervised Learning

IEEE Access
In graph modeling, scarcity of labeled data is a challenging issue. To address this issue, state-of-the-art graph models learn the representation of graph data via contrastive learning.
Peng Qin, Weifu Chen, Min Zhang, Defang Li, Guocan Feng   +4 more
doaj   +1 more source