论文标题
学习与潜在高斯流程ODES相互作用的动态系统
Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs
论文作者
论文摘要
我们研究相互作用对象连续时间动力学的时间不确定性感知模型。我们引入了一个新模型，该模型从其交互中精确地分解了单个对象的独立动力学。通过采用潜在的高斯流程普通微分方程，我们的模型既渗透了独立的动力学及其与可靠的不确定性估计值的相互作用。在我们的公式中，每个对象都表示为图节点，并且通过累积来自相邻对象的消息来建模交互。我们表明，使用现代变化稀疏的高斯工艺推理技术，可以有效地推断这种复杂的变量网络。我们从经验上证明，我们的模型提高了基于神经网络的替代方案的长期预测的可靠性，并且成功处理缺失动态或静态信息。此外，我们观察到，只有我们的模型才能成功地将独立的动态和交互信息封装在不同的功能中，并在推断场景中显示出这种分离的好处。
We study time uncertainty-aware modeling of continuous-time dynamics of interacting objects. We introduce a new model that decomposes independent dynamics of single objects accurately from their interactions. By employing latent Gaussian process ordinary differential equations, our model infers both independent dynamics and their interactions with reliable uncertainty estimates. In our formulation, each object is represented as a graph node and interactions are modeled by accumulating the messages coming from neighboring objects. We show that efficient inference of such a complex network of variables is possible with modern variational sparse Gaussian process inference techniques. We empirically demonstrate that our model improves the reliability of long-term predictions over neural network based alternatives and it successfully handles missing dynamic or static information. Furthermore, we observe that only our model can successfully encapsulate independent dynamics and interaction information in distinct functions and show the benefit from this disentanglement in extrapolation scenarios.
