Robust Graph Neural Networks via Ensemble Learning
Graph neural networks (GNNs) have demonstrated a remarkable ability in the task of semi-supervised node classification. However, most existing GNNs suffer from the nonrobustness issues, which poses a great challenge for applying GNNs into sensitive scenarios. Some researchers concentrate on construc...
Main Authors: | Qi Lin, Shuo Yu, Ke Sun, Wenhong Zhao, Osama Alfarraj, Amr Tolba, Feng Xia |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/10/8/1300 |
Similar Items
-
A Cybersecurity Knowledge Graph Completion Method Based on Ensemble Learning and Adversarial Training
by: Peng Wang, et al.
Published: (2022-12-01) -
Ensemble clustering for graphs: comparisons and applications
by: Valérie Poulin, et al.
Published: (2019-07-01) -
Infinite Ergodic Walks in Finite Connected Undirected Graphs
by: Dimitri Volchenkov
Published: (2021-02-01) -
Dynamic graph neural network with adaptive edge attributes for air quality prediction: A case study in China
by: Jing Xu, et al.
Published: (2023-07-01) -
FedNets: Federated Learning on Edge Devices Using Ensembles of Pruned Deep Neural Networks
by: Besher Alhalabi, et al.
Published: (2023-01-01)