PGODE: Towards High-quality System Dynamics Modeling
It addresses the challenge of predicting interacting dynamics in multi-agent systems, which is incremental as it builds on existing graph neural network methods by adding prototype decomposition for better generalization.
This paper tackles the problem of modeling multi-agent dynamical systems under challenging scenarios like out-of-distribution shift and complex rules, proposing PGODE which incorporates prototype decomposition into a continuous graph ODE framework to enhance generalization, with experiments showing superiority over baselines in both in-distribution and out-of-distribution settings.
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.