Towards agent-based-model informed neural networks
This work addresses the challenge of enforcing constraints like mass conservation in neural networks for complex systems modeling, which is incremental as it builds on existing neural differential equations and graph neural networks.
The authors tackled the problem of designing neural networks that adhere to agent-based model principles, such as mass conservation and information locality, by introducing Agent-Based-Model informed Neural Networks (ABM-NNs). They validated the framework in case studies, including outperforming state-of-the-art graph learning baselines in forecasting and noise robustness for a contagion model.
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