Author(s)

Kenji Nakamura^*, Laura Schneider

Affiliation(s)

School of Mathematics and Statistics, University of Melbourne, Melbourne 3010, Victoria, Australia.

Corresponding Author

Kenji Nakamura

ABSTRACT

Modern supply chains face unprecedented challenges from diverse and interconnected risk sources, including supplier network disruptions, climate change impacts, and volatile market dynamics. Traditional risk assessment methods struggle to capture the complex, heterogeneous relationships inherent in global supply networks. This paper proposes a novel framework leveraging Heterogeneous Graph Transformers for comprehensive, end-to-end supply chain risk assessment. Our approach integrates multi-source heterogeneous information from supplier networks, climate data, and market dynamics into a unified graph representation that captures system structure, behavior, and strategic elements. The framework employs a specialized graph transformer architecture with multi-head attention mechanisms and edge feature integration to model different node types including suppliers, facilities, and products, alongside diverse relationship types such as procurement dependencies, logistics connections, and climate exposure linkages. Through experiments on multi-tier supply chain networks, we demonstrate superior performance in risk prediction accuracy compared to conventional graph neural network approaches, with particular effectiveness in identifying cascading risk propagation patterns across hierarchical supply structures. The framework provides interpretable risk assessments across multiple organizational levels, enabling proactive supply chain risk management strategies that account for node-level vulnerabilities, network-level topologies, and link-level dependencies.

KEYWORDS

Heterogeneous graph transformers; Supply chain risk assessment; Graph neural networks; Climate risk; Multi-tier networks; Market dynamics

CITE THIS PAPER

Kenji Nakamura, Laura Schneider. Heterogeneous graph transformers for end-to-end supply chain risk assessment: integrating supplier networks, climate data, and market dynamics. Innovation and Technology Studies. 2025, 2(2): 15-29. DOI: https://doi.org/10.61784/its3018.

REFERENCES

[1] Kosasih EE, Margaroli F, Gelli S, et al. Towards knowledge graph reasoning for supply chain risk management using graph neural networks. International Journal of Production Research, 2024, 62(15): 5596-5612.

[2] Qiu L. Reinforcement Learning Approaches for Intelligent Control of Smart Building Energy Systems with Real-Time Adaptation to Occupant Behavior and Weather Conditions. Journal of Computing and Electronic Information Management, 2025, 18(2): 32-37.

[3] Zhang H. Physics-Informed Neural Networks for High-Fidelity Electromagnetic Field Approximation in VLSI and RF EDA Applications. Journal of Computing and Electronic Information Management, 2025, 18(2): 38-46.

[4] Koc E, Cetiner B, Rose A, et al. CRAFT: Comprehensive resilience assessment framework for transportation systems in urban areas. Advanced Engineering Informatics, 2020, 46: 101159.

[5] Xie W, He J, Huang F, et al. Supply chain financial fraud detection based on graph neural network and knowledge graph. Tehni?ki vjesnik, 2024, 31(6): 2055-2063.

[6] Zhou Z, Bi K, Zhong Y, et al. HKTGNN: hierarchical knowledge transferable graph neural network-based supply chain risk assessment. In 2023 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), 2023: 772-782.

[7] Tu Y, Chen X, Liu W, et al. Using graph neural network to conduct supplier recommendation based on large-scale supply chain. International Journal of Production Research, 2024, 62(24):8595-8608.

[8] Wang Y, Ding G, Zeng Z, et al. Causal-Aware Multimodal Transformer for Supply Chain Demand Forecasting: Integrating Text, Time Series, and Satellite Imagery. IEEE Access, 2025.

[9] Dwivedi VP, Bresson X. A generalization of transformer networks to graphs. arXiv preprint arXiv:2012.09699, 2020.

[10] Lu Z, Fang Y, Yang C, et al. Heterogeneous graph transformer with poly-tokenization. International Joint Conferences on Artificial Intelligence, 2024.

[11] Izaguirre C, Losada IJ, Camus P, et al. Climate change risk to global port operations. Nature Climate Change, 2021, 11(1): 14-20.

[12] Wang D, Guan D, Zhu S, et al. Economic footprint of California wildfires in 2018. Nature Sustainability, 2021, 4(3): 252-260.

[13] Teale N, Quiring SM. Lessons learned from evaluating the climate change risk on a company's supply chain. Bulletin of the American Meteorological Society, 2025, 106(1): E1-E15.

[14] Rahman MS. Electric Vehicles Historical Sales, Minerals Demand Risks, and Supply Chain Dynamics. Master's thesis, South Dakota State University, 2025.

[15] Yusof ZB. Analyzing the role of predictive analytics and machine learning techniques in optimizing inventory management and demand forecasting for e-commerce. International Journal of Applied Machine Learning, 2024, 4(11): 16-31.

[16] Sfiligoj T, Peperko A, Bajec P, et al. Node importance corresponds to passenger demand in public transport networks. Physica A: Statistical Mechanics and its Applications, 2025, 659: 130354.

[17] Liu CF, Mostafavi A. Network dynamics of community resilience and recovery: new frontier in disaster research. International Journal of Disaster Risk Reduction, 2025, 123: 105489.

[18] Qiu L. Multi-Agent Reinforcement Learning for Coordinated Smart Grid and Building Energy Management Across Urban Communities. Computer Life, 2025, 13(3): 8-15.

[19] Li J, Fan L, Wang X, et al. Product demand prediction with spatial graph neural networks. Applied Sciences, 2024, 14(16):6989.

[20] Wiedmer R, Griffis SE. Structural characteristics of complex supply chain networks. Journal of Business Logistics, 2021, 42(2): 264-290.

[21] Wu B, Chao KM, Li Y, et al. Heterogeneous graph neural networks for fraud detection and explanation in supply chain finance. Information Systems, 2024, 121: 102335.

[22] Qiu L. Machine Learning Approaches to Minimize Carbon Emissions through Optimized Road Traffic Flow and Routing. Frontiers in Environmental Science and Sustainability, 2025, 2(1): 30-41.

[23] Ma Z, Chen X, Sun T, et al. Blockchain-based zero-trust supply chain security integrated with deep reinforcement learning for inventory optimization. Future Internet, 2024, 16(5): 163.

[24] Cao W, Mai NT, Liu W, et al. Adaptive knowledge assessment via symmetric hierarchical Bayesian neural networks with graph symmetry-aware concept dependencies. Symmetry, 2025, 17(8): 1332.

[25] Mai NT, Cao W, Wang Y, et al. The global belonging support framework: Enhancing equity and access for international graduate students. Journal of International Students, 2025, 15(9): 141-160.

[26] Zhang Q, Chen S, Liu W, et al. Balanced Knowledge Transfer in MTTL-ClinicalBERT: A Symmetrical Multi-Task Learning Framework for Clinical Text Classification. Symmetry, 2025, 17(6): 823.

[27] Liu Y, Ren S, Wang X, et al. Temporal logical attention network for log-based anomaly detection in distributed systems. Sensors, 2024, 24(24): 7949.

[28] Zheng W, Liu W. Symmetry-Aware Transformers for Asymmetric Causal Discovery in Financial Time Series. Symmetry, 2025, 17(10): 1591.

[29] Sun T, Yang J, Li J, et al. Enhancing auto insurance risk evaluation with transformer and SHAP. IEEE Access, 2024.

[30] Mai NT, Cao W, Liu W, et al. Interpretable knowledge tracing via transformer-Bayesian hybrid networks: Learning temporal dependencies and causal structures in educational data. Applied Sciences, 2025, 15(17): 9605.

[31] Chen S, Liu Y, Zhang Q, et al. Multi‐Distance Spatial‐Temporal Graph Neural Network for Anomaly Detection in Blockchain Transactions. Advanced Intelligent Systems, 2025: 2400898.

[32] Ren S, Jin J, Niu G, et al. ARCS: Adaptive Reinforcement Learning Framework for Automated Cybersecurity Incident Response Strategy Optimization. Applied Sciences, 2025, 15(2):951.

[33] Tan Y, Wu B, Cao J, et al. LLaMA-UTP: Knowledge-Guided Expert Mixture for Analyzing Uncertain Tax Positions. IEEE Access, 2025.

[34] Ge Y, Wang Y, Liu J, et al. GAN-Enhanced Implied Volatility Surface Reconstruction for Option Pricing Error Mitigation. IEEE Access, 2025.