Saved in:
Bibliographic Details
Main Authors: Luo, Xiao, Gu, Yiyang, Jiang, Huiyu, Zhou, Hang, Huang, Jinsheng, Ju, Wei, Xiao, Zhiping, Zhang, Ming, Sun, Yizhou
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.06554
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911934305009664
author Luo, Xiao
Gu, Yiyang
Jiang, Huiyu
Zhou, Hang
Huang, Jinsheng
Ju, Wei
Xiao, Zhiping
Zhang, Ming
Sun, Yizhou
author_facet Luo, Xiao
Gu, Yiyang
Jiang, Huiyu
Zhou, Hang
Huang, Jinsheng
Ju, Wei
Xiao, Zhiping
Zhang, Ming
Sun, Yizhou
contents This paper studies the problem of modeling multi-agent dynamical systems, where agents could interact mutually to influence their behaviors. Recent research predominantly uses geometric graphs to depict these mutual interactions, which are then captured by powerful graph neural networks (GNNs). However, predicting interacting dynamics in challenging scenarios such as out-of-distribution shift and complicated underlying rules remains unsolved. In this paper, we propose a new approach named Prototypical Graph ODE (PGODE) to address the problem. The core of PGODE is to incorporate prototype decomposition from contextual knowledge into a continuous graph ODE framework. Specifically, PGODE employs representation disentanglement and system parameters to extract both object-level and system-level contexts from historical trajectories, which allows us to explicitly model their independent influence and thus enhances the generalization capability under system changes. Then, we integrate these disentangled latent representations into a graph ODE model, which determines a combination of various interacting prototypes for enhanced model expressivity. The entire model is optimized using an end-to-end variational inference framework to maximize the likelihood. Extensive experiments in both in-distribution and out-of-distribution settings validate the superiority of PGODE compared to various baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2311_06554
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PGODE: Towards High-quality System Dynamics Modeling
Luo, Xiao
Gu, Yiyang
Jiang, Huiyu
Zhou, Hang
Huang, Jinsheng
Ju, Wei
Xiao, Zhiping
Zhang, Ming
Sun, Yizhou
Machine Learning
This paper studies the problem of modeling multi-agent dynamical systems, where agents could interact mutually to influence their behaviors. Recent research predominantly uses geometric graphs to depict these mutual interactions, which are then captured by powerful graph neural networks (GNNs). However, predicting interacting dynamics in challenging scenarios such as out-of-distribution shift and complicated underlying rules remains unsolved. In this paper, we propose a new approach named Prototypical Graph ODE (PGODE) to address the problem. The core of PGODE is to incorporate prototype decomposition from contextual knowledge into a continuous graph ODE framework. Specifically, PGODE employs representation disentanglement and system parameters to extract both object-level and system-level contexts from historical trajectories, which allows us to explicitly model their independent influence and thus enhances the generalization capability under system changes. Then, we integrate these disentangled latent representations into a graph ODE model, which determines a combination of various interacting prototypes for enhanced model expressivity. The entire model is optimized using an end-to-end variational inference framework to maximize the likelihood. Extensive experiments in both in-distribution and out-of-distribution settings validate the superiority of PGODE compared to various baselines.
title PGODE: Towards High-quality System Dynamics Modeling
topic Machine Learning
url https://arxiv.org/abs/2311.06554