Results 321 to 330 of about 1,708,308 (346)

NRGNN: Learning a Label Noise Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs

Knowledge Discovery and Data Mining, 2021
Graph Neural Networks (GNNs) have achieved promising results for semi-supervised learning tasks on graphs such as node classification. Despite the great success of GNNs, many real-world graphs are often sparsely and noisily labeled, which could ...
Enyan Dai, C. Aggarwal, Suhang Wang
semanticscholar   +1 more source

BigST: Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks

Proceedings of the VLDB Endowment
Spatio-Temporal Graph Neural Network (STGNN) has been used as a common workhorse for traffic forecasting. However, most of them require prohibitive quadratic computational complexity to capture long-range spatio-temporal dependencies, thus hindering ...
Jindong Han, Weijiao Zhang, Hao Liu, Tao Tao, Naiqiang Tan, Hui Xiong   +5 more
semanticscholar   +1 more source

Reconstructed Graph Neural Network With Knowledge Distillation for Lightweight Anomaly Detection

IEEE Transactions on Neural Networks and Learning Systems
The proliferation of Internet-of-Things (IoT) technologies in modern smart society enables massive data exchange for offering intelligent services.
Xiaokang Zhou, Jiayi Wu, Wei Liang, K. Wang, Zheng Yan, Laurence T. Yang, Qun Jin   +6 more
semanticscholar   +1 more source

G2ViT: Graph Neural Network-Guided Vision Transformer Enhanced Network for retinal vessel and coronary angiograph segmentation

Neural Networks
Blood vessel segmentation is a crucial stage in extracting morphological characteristics of vessels for the clinical diagnosis of fundus and coronary artery disease. However, traditional convolutional neural networks (CNNs) are confined to learning local
Hao Xu, Yun Wu
semanticscholar   +1 more source

Graph Neural Networks in Cheminformatics

2021
Graph neural networks represent nowadays the most effective machine learning technology in the biochemistry domain. Learning on the huge amount of chemical data can take an important part in finding new molecules or new drugs, which is a crucial research work in cheminformatics.
H. N. Tran Tran, J. Joshua Thomas, Nurul Hashimah Ahamed Hassain Malim, Abdalla M. Ali, Bach Huynh Son   +4 more
openaire   +1 more source

Neural Networks Are Graphs! Graph Neural Networks for Equivariant Processing of Neural Networks

2023
Neural networks that can process the parameters of other neural networks find applications in diverse domains, including processing implicit neural representations, domain adaptation of pretrained networks, generating neural network weights, and predicting generalization errors.
Zhang, D.W., Kofinas, M., Zhang, Y., Chen, Y., Burghouts, G.J., Snoek, C.G.M.   +5 more
openaire   +1 more source

Graph Ensemble Neural Network

Information Fusion, 2023
Rui Duan 0003, Chungang Yan, Junli Wang 0001, Changjun Jiang 0002   +3 more
openaire   +1 more source

Learning Graph Matching with Graph Neural Networks

Graph matching aims at evaluating the dissimilarity of two graphs by defining a constrained correspondence between their nodes and edges. Error-tolerant graph matching, for instance, introduces the concept of a cost for penalizing structural differences in the matching.
Kalvin Dobler, Kaspar Riesen
openaire   +1 more source

Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network for Hyperspectral Image Classification

IEEE Transactions on Image Processing, 2022
Yanni Dong, Quanwei Liu, Bo Du
exaly  

Graph neural network for traffic forecasting: A survey

Expert Systems With Applications, 2022
Weiwei Jiang
exaly