Towards agent-based-model informed neural networks

TL;DR

This paper introduces ABM-NNs, a new neural network framework that incorporates principles of agent-based models to better model complex systems with constraints like conservation laws, validated through diverse case studies.

Contribution

The authors develop a novel framework for neural networks that integrates agent-based model principles, enabling structure-preserving and interpretable dynamics in complex systems.

Findings

Successfully recover ground-truth parameters in Lotka-Volterra systems.

Outperform state-of-the-art graph models in contagion forecasting.

Learned macroeconomic dynamics enable counterfactual policy analysis.

Abstract

In this article, we present a framework for designing neural networks that remain consistent with the underlying principles of agent-based models. We begin by highlighting the limitations of standard neural differential equations in modeling complex systems, where physical invariants (like energy) are often absent but other constraints (like mass conservation, information locality, bounded rationality) must be enforced. To address this, we introduce Agent-Based-Model informed Neural Networks (ABM-NNs), which leverage restricted graph neural networks and hierarchical decomposition to learn interpretable, structure-preserving dynamics. We validate the framework across three case studies of increasing complexity: (i) a generalized Generalized Lotka--Volterra system, where we recover ground-truth parameters from short trajectories in presence of interventions; (ii) a graph-based SIR contagion model, where our method outperforms state-of-the-art graph learning baselines (GCN, GraphSAGE, Graph Transformer) in out-of-sample forecasting and noise robustness; and (iii) a real-world macroeconomic model of the ten largest economies, where we learn coupled GDP dynamics from empirical data and demonstrate counterfactual analysis for policy interventions