CLGNN is a contrastive-learning GNN that predicts temporal betweenness centrality with lower error and higher ranking quality than existing static and temporal GNN baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CLGNN: A Contrastive Learning-based GNN Model for Betweenness Centrality Prediction on Temporal Graphs
CLGNN is a contrastive-learning GNN that predicts temporal betweenness centrality with lower error and higher ranking quality than existing static and temporal GNN baselines.