IVGAE-TAMA-BO: A novel temporal dynamic variational graph model for link prediction in global food trade networks with momentum structural memory and Bayesian optimization

2025-11-03

AI Summary

This paper addresses dynamic link prediction in the global food trade network—a previously unexplored problem. Methodologically, we propose the first dynamic graph neural network tailored to this domain, built upon the Inductive Variational Graph Auto-Encoder (IVGAE) framework. We introduce two key innovations: a trade-aware momentum aggregator (TAMA) and a momentum-driven structured memory mechanism, both explicitly modeling time-varying topological evolution induced by geopolitical, economic, and environmental factors. Hyperparameter optimization is automated via Bayesian optimization. Extensive experiments on five crop-specific real-world datasets demonstrate that our model significantly outperforms static IVGAE and state-of-the-art dynamic baselines across all metrics—achieving superior link prediction accuracy, enhanced temporal dependency capture, and improved cross-temporal generalization. The approach delivers an interpretable, robust modeling paradigm for early-warning systems in food security and resilience assessment of agri-food supply chains.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Global food trade plays a crucial role in ensuring food security and maintaining supply chain stability. However, its network structure evolves dynamically under the influence of geopolitical, economic, and environmental factors, making it challenging to model and predict future trade links. Effectively capturing temporal patterns in food trade networks is therefore essential for improving the accuracy and robustness of link prediction. This study introduces IVGAE-TAMA-BO, a novel dynamic graph neural network designed to model evolving trade structures and predict future links in global food trade networks. To the best of our knowledge, this is the first work to apply dynamic graph neural networks to this domain, significantly enhancing predictive performance. Building upon the original IVGAE framework, the proposed model incorporates a Trade-Aware Momentum Aggregator (TAMA) to capture the temporal evolution of trade networks, jointly modeling short-term fluctuations and long-term structural dependencies. A momentum-based structural memory mechanism further improves predictive stability and performance. In addition, Bayesian optimization is used to automatically tune key hyperparameters, enhancing generalization across diverse trade scenarios. Extensive experiments on five crop-specific datasets demonstrate that IVGAE-TAMA substantially outperforms the static IVGAE and other dynamic baselines by effectively modeling temporal dependencies, while Bayesian optimization further boosts performance in IVGAE-TAMA-BO. These results highlight the proposed framework as a robust and scalable solution for structural prediction in global trade networks, with strong potential for applications in food security monitoring and policy decision support.

Problem

• Modeling evolving trade structures in global food networks
• Predicting future trade links under dynamic influences
• Capturing temporal patterns for improved prediction accuracy

Innovation

• Dynamic graph neural network models evolving trade structures
• Momentum aggregator captures short-term and long-term dependencies
• Bayesian optimization automatically tunes hyperparameters for generalization