Continuous Dynamic Modeling via Neural ODEs for Popularity Trajectory Prediction

2024-10-24

arXiv.org

AI Summary

Existing approaches typically model information cascade popularity prediction as a discrete problem or rely on pre-specified diffusion mechanisms, failing to capture its continuous dynamic evolution. This paper introduces Neural Ordinary Differential Equations (Neural ODEs) for the first time to model popularity trajectory prediction, proposing a continuous dynamical system in latent space that jointly governs structural and temporal co-evolution. We design a dual-perspective encoder to jointly represent cascade topology and temporal patterns, and couple it with an ODE-based generative module enabling fine-grained trajectory inference at arbitrary time points. The framework eliminates reliance on hand-crafted diffusion assumptions and supports end-to-end differentiable training. Extensive experiments on three real-world datasets demonstrate significant improvements over state-of-the-art methods, validating the dual advantages of continuous dynamical modeling—superior predictive accuracy and enhanced interpretability.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

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

Abstract

Popularity prediction for information cascades has significant applications across various domains, including opinion monitoring and advertising recommendations. While most existing methods consider this as a discrete problem, popularity actually evolves continuously, exhibiting rich dynamic properties such as change rates and growth patterns. In this paper, we argue that popularity trajectory prediction is more practical, as it aims to forecast the entire trajectory of how popularity unfolds over arbitrary future time. This approach offers insights into both instantaneous popularity and the underlying dynamic properties. However, traditional methods for popularity trajectory prediction primarily rely on specific diffusion mechanism assumptions, which may not align well with real-world dynamics and compromise their performance. To address these limitations, we propose NODEPT, a novel approach based on neural ordinary differential equations (ODEs) for popularity trajectory prediction. NODEPT models the continuous dynamics of the underlying diffusion system using neural ODEs. We first employ an encoder to initialize the latent state representations of information cascades, consisting of two representation learning modules that capture the co-evolution structural characteristics and temporal patterns of cascades from different perspectives. More importantly, we then introduce an ODE-based generative module that learns the dynamics of the diffusion system in the latent space. Finally, a decoder transforms the latent state into the prediction of the future popularity trajectory. Our experimental results on three real-world datasets demonstrate the superiority and rationality of the proposed NODEPT method.

Problem

• Modeling continuous popularity dynamics in information cascades
• Predicting entire popularity trajectories over arbitrary future time
• Overcoming limitations of discrete methods and diffusion assumptions

Innovation

• Neural ODEs model continuous diffusion dynamics
• Encoder captures co-evolution structural characteristics
• ODE-based generative module learns latent dynamics