Resilience Inference for Supply Chains with Hypergraph Neural Network

2025-11-09

AI Summary

This paper addresses the challenge of modeling high-order, multi-entity dependencies in supply chains with unknown dynamic equations by formally introducing the problem of *supply chain resilience inference*: predicting a system’s capacity to maintain core functionality under disruptions, using only hypergraph topology and historical inventory trajectories. Methodologically, we propose a Hypergraph Neural Network (HGNN) that explicitly captures multi-order interactions—e.g., among firms, products, and tasks—via set-based encoding and hyperedge-level message passing, thereby circumventing reliance on explicit dynamical equations. In supervised learning experiments on synthetic benchmark data, our HGNN significantly outperforms baselines including MLPs, GNN variants, and ResInf, achieving a 12.6% improvement in AUC for early-risk warning. These results empirically validate the critical role of hypergraph structure in resilience modeling.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Supply chains are integral to global economic stability, yet disruptions can swiftly propagate through interconnected networks, resulting in substantial economic impacts. Accurate and timely inference of supply chain resilience the capability to maintain core functions during disruptions is crucial for proactive risk mitigation and robust network design. However, existing approaches lack effective mechanisms to infer supply chain resilience without explicit system dynamics and struggle to represent the higher-order, multi-entity dependencies inherent in supply chain networks. These limitations motivate the definition of a novel problem and the development of targeted modeling solutions. To address these challenges, we formalize a novel problem: Supply Chain Resilience Inference (SCRI), defined as predicting supply chain resilience using hypergraph topology and observed inventory trajectories without explicit dynamic equations. To solve this problem, we propose the Supply Chain Resilience Inference Hypergraph Network (SC-RIHN), a novel hypergraph-based model leveraging set-based encoding and hypergraph message passing to capture multi-party firm-product interactions. Comprehensive experiments demonstrate that SC-RIHN significantly outperforms traditional MLP, representative graph neural network variants, and ResInf baselines across synthetic benchmarks, underscoring its potential for practical, early-warning risk assessment in complex supply chain systems.

Problem

• Inferring supply chain resilience without explicit system dynamics
• Modeling higher-order multi-entity dependencies in supply networks
• Predicting resilience using hypergraph topology and inventory data

Innovation

• Hypergraph neural network models supply chain dependencies
• Set-based encoding captures multi-party firm-product interactions
• Hypergraph message passing infers resilience without dynamic equations