用图扩散网络学习个体行为，让复杂系统模拟可优化、可预测。
Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networks
- 用扩散模型+图神经网络直接建模个体行为，保持系统底层动态
- 在两种模型上复现个体模式并准确预测未来演化趋势
- 适合想用真实数据训练复杂系统模型的研究者
基于代理的模型（ABMs）是研究复杂系统涌现现象的强大工具。在这些模型中，代理行为由局部交互和随机规则决定，但这类规则通常不可微，限制了梯度方法在优化中的应用，也阻碍了与现实数据的融合。本文提出一种新框架，通过观察生成数据来学习任意ABM的可微分代理。该方法结合扩散模型以捕捉行为随机性，以及图神经网络以建模代理间交互。与以往仅近似系统输出的代理方法不同，本方法实现了根本性转变：不再拟合整体结果，而是直接建模个体行为，保留了定义ABMs的去中心化、自下而上的动态特性。我们在两个经典模型（谢林的隔离模型和捕食者-猎物生态系统）上验证了该方法，结果表明其能准确复现个体层面的模式，并在训练之外成功预测涌现动态。结果展示了扩散模型与图学习结合在数据驱动的ABM仿真中的潜力。
原文摘要 · Abstract (English)
Agent-Based Models (ABMs) are powerful tools for studying emergent properties in complex systems. In ABMs, agent behaviors are governed by local interactions and stochastic rules. However, these rules are, in general, non-differentiable, limiting the use of gradient-based methods for optimization, and thus integration with real-world data. We propose a novel framework to learn a differentiable surrogate of any ABM by observing its generated data. Our method combines diffusion models to capture behavioral stochasticity and graph neural networks to model agent interactions. Distinct from prior surrogate approaches, our method introduces a fundamental shift: rather than approximating system-level outputs, it models individual agent behavior directly, preserving the decentralized, bottom-up dynamics that define ABMs. We validate our approach on two ABMs (Schelling's segregation model and a Predator-Prey ecosystem) showing that it replicates individual-level patterns and accurately forecasts emergent dynamics beyond training. Our results demonstrate the potential of combining diffusion models and graph learning for data-driven ABM simulation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。