Oct 21, 2022 · We propose a high-order topology-enhanced graph convolutional network for modeling dynamic graphs. The rationale behind it is that the symmetric substructure ...
Dec 31, 2021 · Understanding the evolutionary mechanisms of dynamic graphs is crucial since dynamic is a basic characteristic of real-world networks.
Understanding the evolutionary mechanisms of dynamic graphs is crucial since dynamic is a basic characteristic of real-world networks.
Dec 5, 2022 · Bibliographic details on High-Order Topology-Enhanced Graph Convolutional Networks for Dynamic Graphs.
We identify two challenges in learning high-order information from temporal graphs, i.e., computational inefficiency and over-smoothing, which cannot be solved ...
High-Order Topology-Enhanced Graph Convolutional Networks for Dynamic Graphs. Symmetry 2022, 14, 2218. https://doi.org/10.3390/sym14102218. AMA Style. Zhu J ...
To address these issues, we propose a high-order topology-enhanced graph convolutional network for modeling dynamic graphs. The rationale behind it is that the ...
People also ask
What is the difference between graph convolutional network and convolutional neural network?
What are graph convolutional networks used for?
Understanding the evolutionary mechanisms of dynamic graphs is crucial since dynamic is a basic characteristic of real-world networks.
A novel model named Dynamic Graph Convolutional Networks by Semi-Supervised Contrastive Learning (DGSCL) is proposed in this paper.
High-Order Topology-Enhanced Graph Convolutional Networks for Dynamic Graphs · Computer Science. Symmetry · 2022.