Uncertainty in GNN Learning Evaluations: A Comparison between Measures for Quantifying Randomness in GNN Community Detection
(1) The enhanced capability of graph neural networks (GNNs) in unsupervised community detection of clustered nodes is attributed to their capacity to encode both the connectivity and feature information spaces of graphs. The identification of latent communities holds practical significance in variou...
Main Authors: | William Leeney, Ryan McConville |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/26/1/78 |
Similar Items
-
Bridge Node Detection between Communities Based on GNN
by: Hairu Luo, et al.
Published: (2022-10-01) -
Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
by: Shuhao Shi, et al.
Published: (2021-11-01) -
Flood-Related Multimedia Benchmark Evaluation: Challenges, Results and a Novel GNN Approach
by: Thomas Papadimos, et al.
Published: (2023-04-01) -
MetaGNN-Based Medical Records Unstructured Specialized Vocabulary Few-Shot Representation Learning
by: Hongxing Ling, et al.
Published: (2022-01-01) -
Joint Multidimensional Pattern for Spectrum Prediction Using GNN
by: Xiaomin Wen, et al.
Published: (2023-11-01)