Modeling Trend Dynamics with Variational Neural ODEs for Information Popularity Prediction

TL;DR

This paper introduces VNOIP, a variational neural ODE-based model that explicitly captures the continuous evolution of information popularity trends in social networks, improving prediction accuracy and efficiency.

Contribution

VNOIP is the first to model popularity trend dynamics with bidirectional jump ODEs and attention, integrating cascade and trend patterns for superior predictions.

Findings

VNOIP outperforms state-of-the-art methods in accuracy.

VNOIP demonstrates high efficiency on real-world datasets.

The model effectively captures long-range dependencies in cascade sequences.

Abstract

Predicting the future popularity of information in online social networks is a crucial yet challenging task, due to the complex spatiotemporal dynamics underlying information diffusion. Existing methods typically use structural or sequential patterns within the observation window as direct inputs for subsequent popularity prediction. However, most approaches lack the ability to explicitly model the overall trend of popularity up to the prediction time, which leads to limited predictive capability. To address these limitations, we propose VNOIP, a novel method based on variational neural Ordinary Differential Equations (ODEs) for information popularity prediction. Specifically, VNOIP introduces bidirectional jump ODEs with attention mechanisms to capture long-range dependencies and bidirectional context within cascade sequences. Furthermore, by jointly considering both cascade patterns and overall trend temporal patterns, VNOIP explicitly models the continuous-time dynamics of popularity trend trajectories with variational neural ODEs. Additionally, a knowledge distillation loss is employed to align the evolution of prior and posterior latent variables. Extensive experiments on real-world datasets demonstrate that VNOIP is highly competitive in both prediction accuracy and efficiency compared to state-of-the-art baselines.