HOPE: High-order Graph ODE For Modeling Interacting Dynamics
HOPE: High-order Graph ODE For Modeling Interacting Dynamics
复制标题
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Xiao Luo;Jingyang Yuan;Zijie Huang;Huiyu Jiang;Yifang Qin;Wei Ju;Ming Zhang;Yizhou Sun
中科院分区：
文献类型：
--
作者：
Xiao Luo;Jingyang Yuan;Zijie Huang;Huiyu Jiang;Yifang Qin;Wei Ju;Ming Zhang;Yizhou Sun
领先的图常微分方程(ODE)模型提供了以数据驱动的方法对相互作用的多智能体动态系统建模的通用策略。它们通常由用于获取初始状态的时态图编码器和用于对动态系统的演化进行建模的基于神经节点的生成模型组成。然而，由于未能对长期时间趋势中的高阶相关性进行建模，现有方法在能力和效率方面存在严重不足。针对这一问题，本文提出了一种从动态交互数据中学习的新模型--高阶图ODE(High-Order Graph ODE)，该模型可以自然地表示为图。该算法首先采用双图编码器对节点和边的潜在状态表示进行初始化，由两个分支组成，以互补的方式获取时空相关性。更重要的是，我们希望利用二阶图ODE函数分别对潜在空间中节点和边的动态进行建模，这使得能够有效地从复杂动态系统中学习长期依赖关系。在多种数据集上的实验结果证明了该方法的有效性和高效性。
Leading graph ordinary differential equation (ODE) models have offered generalized strategies to model interacting multi-agent dynamical systems in a data-driven approach. They typically consist of a temporal graph encoder to get the initial states and a neural ODE-based generative model to model the evolution of dynamical systems. However, existing methods have severe deficiencies in capacity and efficiency due to the failure to model high-order correlations in long-term temporal trends. To tackle this, in this paper, we propose a novel model named High-Order graPh ODE (HOPE) for learning from dynamic interaction data, which can be naturally represented as a graph. It first adopts a twin graph encoder to initialize the latent state representations of nodes and edges, which consists of two branches to capture spatio-temporal correlations in complementary manners. More importantly, our HOPE utilizes a second-order graph ODE function which models the dynamics for both nodes and edges in the latent space respectively, which enables efficient learning of long-term dependencies from complex dynamical systems. Experiment results on a variety of datasets demonstrate both the effectiveness and efficiency of our proposed method.