Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

11/08/2020
by   Zijie Huang, et al.
0

Many real-world systems, such as moving planets, can be considered as multi-agent dynamic systems, where objects interact with each other and co-evolve along with the time. Such dynamics is usually difficult to capture, and understanding and predicting the dynamics based on observed trajectories of objects become a critical research problem in many domains. Most existing algorithms, however, assume the observations are regularly sampled and all the objects can be fully observed at each sampling time, which is impractical for many applications. In this paper, we propose to learn system dynamics from irregularly-sampled partial observations with underlying graph structure for the first time. To tackle the above challenge, we present LG-ODE, a latent ordinary differential equation generative model for modeling multi-agent dynamic system with known graph structure. It can simultaneously learn the embedding of high dimensional trajectories and infer continuous latent system dynamics. Our model employs a novel encoder parameterized by a graph neural network that can infer initial states in an unsupervised way from irregularly-sampled partial observations of structural objects and utilizes neuralODE to infer arbitrarily complex continuous-time latent dynamics. Experiments on motion capture, spring system, and charged particle datasets demonstrate the effectiveness of our approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/27/2019

ODE^2VAE: Deep generative second order ODEs with Bayesian neural networks

We present Ordinary Differential Equation Variational Auto-Encoder (ODE^...
research
02/25/2019

Stochastic Prediction of Multi-Agent Interactions from Partial Observations

We present a method that learns to integrate temporal information, from ...
research
07/10/2023

Generalizing Graph ODE for Learning Complex System Dynamics across Environments

Learning multi-agent system dynamics has been extensively studied for va...
research
02/03/2023

Learning to Decouple Complex Systems

A complex system with cluttered observations may be a coupled mixture of...
research
11/19/2022

Autoregressive GNN-ODE GRU Model for Network Dynamics

Revealing the continuous dynamics on the networks is essential for under...
research
02/16/2023

Temporal Graph Neural Networks for Irregular Data

This paper proposes a temporal graph neural network model for forecastin...
research
10/23/2019

An inverse problem approach to the probabilistic reconstruction of particle tracks on a censored and closed surface

Investigation of dynamics processes in cell biology very often relies on...

Please sign up or login with your details

Forgot password? Click here to reset