BriefGPT.xyz
Feb, 2022
使用图神经网络学习复杂系统的动力学和结构
Learning Dynamics and Structure of Complex Systems Using Graph Neural Networks
HTML
PDF
Zhe Li, Andreas S. Tolias, Xaq Pitkow
TL;DR
本研究训练了图神经网络以适应来自非线性动力系统的时间序列,发现了学习表示和模型组件的简单解释,并成功地确定了'图翻译器',使两种新类型广义:仅基于时间序列观测来恢复新系统实例的潜在结构,或者直接从该结构构造新网络。结果表明,理解复杂系统的动态和结构及其如何用于泛化的途径。
Abstract
Many complex systems are composed of interacting parts, and the underlying laws are usually simple and universal. While
graph neural networks
provide a useful relational inductive bias for modeling such systems,
general
→