GNN-Based Candidate Node Predictor for Influence Maximization in Temporal Graphs

2025-03-31

AI Summary

Traditional influence maximization methods struggle to adapt to rapidly evolving topologies in dynamic social networks. To address this, we propose a temporal-aware joint modeling framework that integrates Graph Neural Networks (GNNs) with Bidirectional Long Short-Term Memory (BiLSTM) networks—marking the first approach to jointly model structural evolution and temporal dependencies. Specifically, GNNs encode local graph topology, while BiLSTM captures bidirectional temporal patterns across historical and future graph states, enabling dynamic, adaptive prediction of candidate seed nodes. Evaluated on multiple real-world temporal graph datasets, our model achieves an average prediction accuracy of 90%, significantly reducing computational overhead for seed evaluation. This work provides an efficient, scalable solution for real-time influence optimization tasks such as viral marketing and opinion guidance.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In an age where information spreads rapidly across social media, effectively identifying influential nodes in dynamic networks is critical. Traditional influence maximization strategies often fail to keep up with rapidly evolving relationships and structures, leading to missed opportunities and inefficiencies. To address this, we propose a novel learning-based approach integrating Graph Neural Networks (GNNs) with Bidirectional Long Short-Term Memory (BiLSTM) models. This hybrid framework captures both structural and temporal dynamics, enabling accurate prediction of candidate nodes for seed set selection. The bidirectional nature of BiLSTM allows our model to analyze patterns from both past and future network states, ensuring adaptability to changes over time. By dynamically adapting to graph evolution at each time snapshot, our approach improves seed set calculation efficiency, achieving an average of 90% accuracy in predicting potential seed nodes across diverse networks. This significantly reduces computational overhead by optimizing the number of nodes evaluated for seed selection. Our method is particularly effective in fields like viral marketing and social network analysis, where understanding temporal dynamics is crucial.

Problem

• Identifying influential nodes in dynamic social networks efficiently
• Overcoming limitations of traditional influence maximization in evolving graphs
• Reducing computational costs while maintaining high seed selection accuracy

Innovation

• GNN and BiLSTM hybrid for dynamic networks
• Bidirectional temporal pattern analysis
• Efficient seed set prediction with 90% accuracy