Physics-Informed Neural Network with Adaptive Clustering Learning Mechanism for Information Popularity Prediction

Abstract

With society entering the Internet era, the volume and speed of data and information have been increasing. Predicting the popularity of information cascades can help with high-value information delivery and public opinion monitoring on the internet platforms. The current state-of-the-art models for predicting information popularity utilize deep learning methods such as graph convolution networks (GCNs) and recurrent neural networks (RNNs) to capture early cascades and temporal features to predict their popularity increments. However, these previous methods mainly focus on the micro features of information cascades, neglecting their general macroscopic patterns. Furthermore, they also lack consideration of the impact of information heterogeneity on spread popularity. To overcome these limitations, we propose a physics-informed neural network with adaptive clustering learning mechanism, PIACN, for predicting the popularity of information cascades. Our proposed model not only models the macroscopic patterns of information dissemination through physics-informed approach for the first time but also considers the influence of information heterogeneity through an adaptive clustering learning mechanism. Extensive experimental results on three real-world datasets demonstrate that our model significantly outperforms other state-of-the-art methods in predicting information popularity.

Figures (9)

• Figure 1: Nonlinear function fitting and clustering performance on Twitter, Weibo and APS dataset.
• Figure 2: The formulation of information popularity prediction.
• Figure 3: The shape of the Richards growth curve changes with the variation of the parameter $\delta$.
• Figure 4: The overview of our proposed deep learning model PIACN. PIACN is composed of cascade embedding network, temporal learning network, adaptive clustering network, prediction network and physical modeling network. There are two parts of input, information cascades and popularity time series, which are put forward into cascade embedding network and temporal learning network respectively. The loss function of our proposed model consists of three parts: prediction loss $L_{pred}$, physical constraint loss $L_{phy}$, and clustering loss $L_{clu}$.
• Figure 5: The architecture of cascade embedding network. The dynamics of information cascades are embedded into the latent space by self-attention architecture.