Ha Seungwoong, Jeong Hawoong
Department of Physics, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Korea.
Center for Complex Systems, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Korea.
Sci Rep. 2021 Jun 17;11(1):12804. doi: 10.1038/s41598-021-91878-w.
Rich phenomena from complex systems have long intrigued researchers, and yet modeling system micro-dynamics and inferring the forms of interaction remain challenging for conventional data-driven approaches, being generally established by scientists with human ingenuity. In this study, we propose AgentNet, a model-free data-driven framework consisting of deep neural networks to reveal and analyze the hidden interactions in complex systems from observed data alone. AgentNet utilizes a graph attention network with novel variable-wise attention to model the interaction between individual agents, and employs various encoders and decoders that can be selectively applied to any desired system. Our model successfully captured a wide variety of simulated complex systems, namely cellular automata (discrete), the Vicsek model (continuous), and active Ornstein-Uhlenbeck particles (non-Markovian) in which, notably, AgentNet's visualized attention values coincided with the true variable-wise interaction strengths and exhibited collective behavior that was absent in the training data. A demonstration with empirical data from a flock of birds showed that AgentNet could identify hidden interaction ranges exhibited by real birds, which cannot be detected by conventional velocity correlation analysis. We expect our framework to open a novel path to investigating complex systems and to provide insight into general process-driven modeling.
复杂系统中丰富的现象长期以来一直吸引着研究人员，然而，对系统微观动力学进行建模并推断相互作用的形式，对于传统的数据驱动方法来说仍然具有挑战性，这些方法通常是由科学家凭借人类智慧建立起来的。在本研究中，我们提出了AgentNet，这是一个无模型的数据驱动框架，由深度神经网络组成，仅从观测数据中揭示和分析复杂系统中隐藏的相互作用。AgentNet利用具有新颖的逐变量注意力的图注意力网络对个体智能体之间的相互作用进行建模，并采用各种编码器和解码器，这些编码器和解码器可以选择性地应用于任何所需的系统。我们的模型成功捕获了各种各样的模拟复杂系统，即细胞自动机（离散型）、维塞克模型（连续型）和有源奥恩斯坦 - 乌伦贝克粒子（非马尔可夫型），其中值得注意的是，AgentNet的可视化注意力值与真实的逐变量相互作用强度一致，并展现出训练数据中不存在的集体行为。对一群鸟类的经验数据进行的演示表明，AgentNet能够识别真实鸟类表现出的隐藏相互作用范围，而这是传统速度相关性分析无法检测到的。我们期望我们的框架能够为研究复杂系统开辟一条新途径，并为一般的过程驱动建模提供见解。
