# Learning production functions for supply chains with graph neural networks

arXiv: https://arxiv.org/abs/2407.18772 · HTML: https://mlsanity.com/paper/2407.18772/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 69 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 22 of 22)

- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [Incorporating Symmetry into Deep Dynamics Models for Improved Generalization](https://mlsanity.com/paper/2002.03061/) (2020)
- [Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey](https://mlsanity.com/paper/2005.07496/) (2020)
- [Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data](https://mlsanity.com/paper/2006.10833/) (2020)
- [Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities](https://mlsanity.com/paper/2302.01018/) (2023)
- [A Review of Graph Neural Networks in Epidemic Modeling](https://mlsanity.com/paper/2403.19852/) (2024)
- [Data Considerations in Graph Representation Learning for Supply Chain Networks](https://mlsanity.com/paper/2107.10609/) (2021)
- [SupplyGraph: A Benchmark Dataset for Supply Chain Planning using Graph Neural Networks](https://mlsanity.com/paper/2401.15299/) (2024)
- [Detecting Gang-Involved Escalation on Social Media Using Context](https://mlsanity.com/paper/1809.03632/) (2018)
- [ChoiceRank: Identifying Preferences from Node Traffic in Networks](https://mlsanity.com/paper/1610.06525/) (2016)
- [Automatically Inferring Gender Associations from Language](https://mlsanity.com/paper/1909.00091/) (2019)
- [Accurate Measures of Vaccination and Concerns of Vaccine Holdouts from Web Search Logs](https://mlsanity.com/paper/2306.07457/) (2023)
- [Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting](https://mlsanity.com/paper/2402.18697/) (2024)
- [To Recommend or Not? A Model-Based Comparison of Item-Matching Processes](https://mlsanity.com/paper/2110.11468/) (2021)
- [Estimating Geographic Spillover Effects of COVID-19 Policies From Large-Scale Mobility Networks](https://mlsanity.com/paper/2212.06224/) (2022)

## Built on by (most cited first, 2 of 2)

- [Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding](https://mlsanity.com/paper/2505.19825/) (2025)
- [A Theoretical Framework for Graph-based Digital Twins for Supply Chain Management and Optimization](https://mlsanity.com/paper/2504.03692/) (2025)

## Abstract (arXiv)

The global economy relies on the flow of goods over supply chain networks, with nodes as firms and edges as transactions between firms. While we may observe these external transactions, they are governed by unseen production functions, which determine how firms internally transform the input products they receive into output products that they sell. In this setting, it can be extremely valuable to infer these production functions, to improve supply chain visibility and to forecast future transactions more accurately. However, existing graph neural networks (GNNs) cannot capture these hidden relationships between nodes' inputs and outputs. Here, we introduce a new class of models for this setting by combining temporal GNNs with a novel inventory module, which learns production functions via attention weights and a special loss function. We evaluate our models extensively on real supply chains data and data generated from our new open-source simulator, SupplySim. Our models successfully infer production functions, outperforming the strongest baseline by 6%-50% (across datasets), and forecast future transactions, outperforming the strongest baseline by 11%-62%