Results 21 to 30 of about 2,499,483 (247)

Particle Propagation Model for Dynamic Node Classification

IEEE Access, 2020
With the popularity of online social networks, researches on dynamic node classification have received further attention. Dynamic node classification also helps the rapid popularization of online social networks.
Wenzheng Li, Dechun Yin, Deyu Yuan, Benyu Wang, Yijun Gu   +4 more
doaj   +1 more source

DAG: Dual Attention Graph Representation Learning for Node Classification

Mathematics, 2023
Transformer-based graph neural networks have accomplished notable achievements by utilizing the self-attention mechanism for message passing in various domains. However, traditional methods overlook the diverse significance of intra-node representations,
Siyi Lin, Jie Hong, Bo Lang, Lin Huang
doaj   +1 more source

Graph Decipher: A transparent dual‐attention graph neural network to understand the message‐passing mechanism for the node classification

, 2022
Graph neural networks (GNNs) can be effectively applied to solve many real-world problems across widely diverse fields. Their success is inseparable from the message-passing mechanisms evolving over the years.
Shan Ai, Liu, Chao, Chao Liu, Ai, Shan, Zhang, Ji, Yan Pang, Wang, Zhen, Pang, Yan, Lin, Jianwei, Ji Zhang, Teng Huang, Zhen Wang, Jianwei Li, Poorya Hosseini, Hosseini, Poorya, Huang, Teng   +15 more
core   +1 more source

Deep Graph-Convolutional Generative Adversarial Network for Semi-Supervised Learning on Graphs

Remote Sensing, 2023
Graph convolutional networks (GCNs) are neural network frameworks for machine learning on graphs. They can simultaneously perform end-to-end learning on the attribute information and the structure information of graph data.
Nan Jia, Xiaolin Tian, Wenxing Gao, Licheng Jiao   +3 more
doaj   +1 more source

OpenWGL: open-world graph learning for unseen class node classification

, 2021
Graph learning, such as node classification, is typically carried out in a closed-world setting. A number of nodes are labeled, and the learning goal is to correctly classify remaining (unlabeled) nodes into classes, represented by the labeled nodes.
Wu, M, Wu, Man, Pan, Shirui, Zhu, X, Pan, S, Zhu, Xingquan   +5 more
core   +1 more source

Structural Hierarchy-Enhanced Network Representation Learning

Applied Sciences, 2020
Network representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP).
Cheng-Te Li, Hong-Yu Lin
doaj   +1 more source

FinFD-GCN: Using Graph Convolutional Networks for Fraud Detection in Financial Data [PDF]

Journal of Artificial Intelligence and Data Mining
In recent years, new technologies have brought new innovations into the financial and commercial world, giving fraudsters many ways to commit fraud and cost companies big time.
Mohamad Mahdi Yadegar, Hossein Rahmani
doaj   +1 more source

A Dynamic Variational Framework for Open-World Node Classification in Structured Sequences

, 2022
Structured sequences are a popular data representation, used to model complex data such as traffic networks. A key machine learning task for structured sequences is node classification, that is predicting the class labels of unlabeled nodes.
Zhang, Q, Zhang, P, Huang, JZ, Chen, X, Fournier-Viger, P, Li, Q, Pan, S   +6 more
core   +1 more source

Community-hop : enhancing node classification through community preference [PDF]

In recent years, Graph Neural Networks (GNNs) have demonstrated significant influence on the analysis of graph structures by leveraging message-passing mechanisms to aggregate neighborhood information and perform various graph-related tasks from node ...
Begga, Ahmed, Ali, Waqar, Niculescu, Gabriel, Francisco Escolano, Waqar Ali, Stadelmann, Thilo, Pelillo, Marcello, Thilo Stadelmann, Marcello Pelillo, Escolano, Francisco, Gabriel Niculescu, Ahmed Begga   +11 more
core   +1 more source

G2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns

, 2023
Node classification is the task of predicting the labels of unlabeled nodes in a graph. State-of-the-art methods based on graph neural networks achieve excellent performance when all labels are available during training.
Zhang, Q, Zhang, X, Chen, X, Fournier-Viger, P, Shi, Z, Pan, S   +5 more
core   +1 more source