TGNN-Bet: Approximation of Temporal Betweenness Centrality using Temporal Graph Neural Network

Networks appear across various domains, and identifying central nodes in temporal networks is more challenging than in static networks. Temporal betweenness centrality is the widely used method to assess the importance of the nodes. This method is based on shortest temporal path calculations. However, computing this centrality metrics value is computationally intensive, especially for large-scale networks. Various approximation algorithms exist, but they often lack efficiency or accuracy. We introduce TGNN-Bet, a temporal graph neural network model, to approximate temporal betweenness centrality. In TGNN-Bet, each node gathers features from multi-hop neighbors, enabling the model to simulate paths and capture the reachability of nodes. The model’s effectiveness is validated using the Spearman correlation (ρ) performance metric and comparing system runtimes with the existing temporal betweenness centrality method. Experimental results on six real-world temporal networks demonstrate that TGNN-Bet strongly correlates with existing temporal betweenness centrality methods. The proposed TGNN-Bet model achieves an average computation time reduction of 94.216% compared to conventional temporal betweenness centrality methods.