MUST: Multi-Scale Structural-Temporal Link Prediction Model for UAV Ad Hoc Networks

2025-05-14

AI Summary

In adversarial unmanned aerial network (UANET) environments, link prediction remains challenging due to routing information scarcity, highly dynamic and sparse topologies. To address this, we propose a multi-scale temporal graph learning method relying solely on historical topology data. Our approach innovatively integrates three hierarchical graph representations—individual nodes, community structures, and global network topology—and jointly models structural dependencies via graph attention networks (GATs) and cross-scale temporal evolution via long short-term memory (LSTM) units. We further design a sparsity-aware loss function to enhance robustness under extreme sparsity. Evaluated on multiple UANET simulation datasets, our method achieves state-of-the-art performance in both link prediction accuracy and generalization capability, effectively resolving the link predictability problem in highly dynamic, sparse network scenarios.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Link prediction in unmanned aerial vehicle (UAV) ad hoc networks (UANETs) aims to predict the potential formation of future links between UAVs. In adversarial environments where the route information of UAVs is unavailable, predicting future links must rely solely on the observed historical topological information of UANETs. However, the highly dynamic and sparse nature of UANET topologies presents substantial challenges in effectively capturing meaningful structural and temporal patterns for accurate link prediction. Most existing link prediction methods focus on temporal dynamics at a single structural scale while neglecting the effects of sparsity, resulting in insufficient information capture and limited applicability to UANETs. In this paper, we propose a multi-scale structural-temporal link prediction model (MUST) for UANETs. Specifically, we first employ graph attention networks (GATs) to capture structural features at multiple levels, including the individual UAV level, the UAV community level, and the overall network level. Then, we use long short-term memory (LSTM) networks to learn the temporal dynamics of these multi-scale structural features. Additionally, we address the impact of sparsity by introducing a sophisticated loss function during model optimization. We validate the performance of MUST using several UANET datasets generated through simulations. Extensive experimental results demonstrate that MUST achieves state-of-the-art link prediction performance in highly dynamic and sparse UANETs.

Problem

• Predicting future links in UAV networks using historical topology
• Addressing high dynamism and sparsity in UAV network topologies
• Combining multi-scale structural and temporal features for link prediction

Innovation

• Uses multi-scale GATs for structural feature capture
• Employs LSTM networks to learn temporal dynamics
• Introduces loss function to mitigate sparsity impact