Neural relational and dynamics inference for complex systems

Abstract

Many complex processes in the real world can be viewed as complex systems and their evolution is governed by underlying nonlinear dynamics. However, one can only access the trajectories of the system without knowing the underlying system structure and dynamics in most cases. To address this challenge, this paper proposes a model called Neural Relational and Dynamics Inference (NRDI) that combines graph neural networks (GNNs) and ordinary differential equation systems (ODEs) to handle both continuous-time dynamics prediction and network topology inference for complex systems. Our model contains two modules: (1) the network inference module, which infers system structure from input system trajectories using GNNs, and (2) the dynamics learning module, which employs GNNs to fit the differential equation system for predicting future trajectories. We tested NRDI’s performance on system trajectory prediction and graph reconstruction separately. Experimental results show that the proposed NRDI outperforms many baseline models on continuous-time complex network dynamics prediction, and can explicitly infer network structures with high accuracy.