Results 31 to 40 of about 30,335 (256)

Accurate graph classification via two-staged contrastive curriculum learning.

PLoS ONE
Given a graph dataset, how can we generate meaningful graph representations that maximize classification accuracy? Learning representative graph embeddings is important for solving various real-world graph-based tasks.
Sooyeon Shim, Junghun Kim, Kahyun Park, U Kang   +3 more
doaj   +1 more source

Cross-modal Deep Metric Learning with Multi-task Regularization

, 2017
DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data ...
Huang, Xin, Peng, Yuxin
core   +1 more source

Prototypical Graph Contrastive Learning

IEEE Transactions on Neural Networks and Learning Systems
Graph-level representations are critical in various real-world applications, such as predicting the properties of molecules. However, in practice, precise graph annotations are generally very expensive and time-consuming. To address this issue, graph contrastive learning constructs an instance discrimination task, which pulls together positive pairs ...
Shuai Lin, Chen Liu, Pan Zhou, Zi-Yuan Hu, Shuojia Wang, Ruihui Zhao, Yefeng Zheng, Liang Lin, Eric Xing, Xiaodan Liang   +9 more
openaire   +3 more sources

Contrastive Graph Learning for Social Recommendation

Frontiers in Physics, 2022
Owing to the strength in learning representation of the high-order connectivity of graph neural networks (GNN), GNN-based collaborative filtering has been widely adopted in recommender systems.
Yongshuai Zhang, Yongshuai Zhang, Jiajin Huang, Jiajin Huang, Jiajin Huang, Jiajin Huang, Mi Li, Mi Li, Mi Li, Mi Li, Jian Yang, Jian Yang, Jian Yang, Jian Yang   +13 more
doaj   +1 more source

Collaborative filtering via sparse Markov random fields

, 2016
Recommender systems play a central role in providing individualized access to information and services. This paper focuses on collaborative filtering, an approach that exploits the shared structure among mind-liked users and similar items. In particular,
Phung, Dinh, Tran, Truyen, Venkatesh, Svetha   +2 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

Course Recommendation Model Based on Layer Dropout Graph Differential Contrastive Learning

IEEE Access
At present, the course recommendation model of graph collaborative filtering mainly uses bipartite graph modeling to obtain user-course cooperative relationship.
Yong Ouyang, Hao Long, Rong Gao, Jinghang Liu   +3 more
doaj   +1 more source

Line graph contrastive learning for node classification

Journal of King Saud University: Computer and Information Sciences
Existing graph contrastive learning methods often rely on differences in node features within subgraphs, lacking effective capture of the global structural information of the graph.
Mingyuan Li, Lei Meng, Zhonglin Ye, Yuzhi Xiao, Shujuan Cao, Haixing Zhao   +5 more
doaj   +1 more source

Deep Metric Learning via Lifted Structured Feature Embedding

, 2015
Learning the distance metric between pairs of examples is of great importance for learning and visual recognition. With the remarkable success from the state of the art convolutional neural networks, recent works have shown promising results on ...
Jegelka, Stefanie, Savarese, Silvio, Song, Hyun Oh, Xiang, Yu   +3 more
core   +1 more source

Molecular graph contrastive learning with line graph

Pattern Recognition
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 knowledge incorporation.
Xueyuan Chen, Shangzhe Li, Ruomei Liu, Bowen Shi, Jiaheng Liu, Junran Wu, Ke Xu   +6 more
openaire   +2 more sources