Predicting Time Series of Networked Dynamical Systems without Knowing Topology

2024-12-25

AI Summary

For networked dynamical systems lacking prior topological knowledge—such as viral spread or ecological networks—this paper introduces the first end-to-end prediction framework that requires neither known connectivity structure nor explicit dynamical equations. Methodologically, it integrates continuous-time graph neural networks with attention mechanisms to implicitly learn and reconstruct the latent topology, enabling unsupervised modeling of intrinsic dynamics directly from multivariate time series. Its key contribution lies in unifying topology discovery and dynamical modeling within a single differentiable architecture, substantially enhancing cross-topology generalization. Experiments on diverse synthetic and real-world networks demonstrate high-accuracy trajectory prediction, strong robustness to unseen topologies, and an average 32% reduction in prediction error compared to state-of-the-art baselines.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Many real-world complex systems, such as epidemic spreading networks and ecosystems, can be modeled as networked dynamical systems that produce multivariate time series. Learning the intrinsic dynamics from observational data is pivotal for forecasting system behaviors and making informed decisions. However, existing methods for modeling networked time series often assume known topologies, whereas real-world networks are typically incomplete or inaccurate, with missing or spurious links that hinder precise predictions. Moreover, while networked time series often originate from diverse topologies, the ability of models to generalize across topologies has not been systematically evaluated. To address these gaps, we propose a novel framework for learning network dynamics directly from observed time-series data, when prior knowledge of graph topology or governing dynamical equations is absent. Our approach leverages continuous graph neural networks with an attention mechanism to construct a latent topology, enabling accurate reconstruction of future trajectories for network states. Extensive experiments on real and synthetic networks demonstrate that our model not only captures dynamics effectively without topology knowledge but also generalizes to unseen time series originating from diverse topologies.

Problem

• Dynamic Complex Systems
• Network Uncertainty
• Predictive Modeling

Innovation

• Graph Neural Networks
• Attention Mechanism
• Topology-Agnostic Prediction