On the Potential of Graph Neural Networks as Metamodels for Supply Chain Optimization: Dataset, Architectures, and Directions
Machine Learning
Summary
The authors study how Graph Neural Networks (GNNs), a type of machine learning model that works well with graph-shaped data, can help optimize supply chains. They create a large dataset of supply chain graphs with performance results using a simulation tool they developed. Then, they test different GNN setups to predict supply chain behavior more quickly than running full simulations. Their work sets the stage for using GNNs to improve supply chain design and analysis efficiently.
Authors
Tushar Lone, Neha Karanjkar
Abstract
Graph Neural Networks (GNNs) have emerged as a powerful, differentiable class of learning models for graph-structured systems. Their ability to generalize across topologies opens the prospect of a surrogate for combined structural and parametric optimization, which classical metamodels cannot offer. Supply chains are a natural target, yet the use of GNN surrogates for supply chain problems is largely unexplored. This paper lays the foundation, presents initial steps, and discusses key research directions. As a foundation, we formulate the problem and create a large public training dataset of programmatically generated supply chain graphs with input parameters and steady-state performance metrics obtained using our SupplyNetPy simulation library. As initial steps, we explore GNN architectures that work well as surrogates for node- and network-level predictions, and analyze their accuracy-compute trade-off against simulation. Most importantly, we outline the exciting directions this opens, namely gradient-based optimization over topology, fast design-space exploration, and sensitivity analysis.