Explicit Time Embedding Based Cascade Attention Network for Information Popularity Prediction

TL;DR

This paper introduces TCAN, a novel neural network architecture that integrates temporal attributes and cascade role information for improved large-scale information popularity prediction in social networks.

Contribution

It proposes an explicit time embedding approach combined with cascade graph and sequence attention encoders, unifying temporal and cascade information for better prediction performance.

Findings

TCAN achieves lower MSLE and MAE compared to baselines.

It outperforms other models by over 10% in MSLE and R-squared.

The method maintains good interpretability and efficiency.

Abstract

Predicting information cascade popularity is a fundamental problem in social networks. Capturing temporal attributes and cascade role information (e.g., cascade graphs and cascade sequences) is necessary for understanding the information cascade. Current methods rarely focus on unifying this information for popularity predictions, which prevents them from effectively modeling the full properties of cascades to achieve satisfactory prediction performances. In this paper, we propose an explicit Time embedding based Cascade Attention Network (TCAN) as a novel popularity prediction architecture for large-scale information networks. TCAN integrates temporal attributes (i.e., periodicity, linearity, and non-linear scaling) into node features via a general time embedding approach (TE), and then employs a cascade graph attention encoder (CGAT) and a cascade sequence attention encoder (CSAT) to fully learn the representation of cascade graphs and cascade sequences. We use two real-world datasets (i.e., Weibo and APS) with tens of thousands of cascade samples to validate our methods. Experimental results show that TCAN obtains mean logarithm squared errors of 2.007 and 1.201 and running times of 1.76 hours and 0.15 hours on both datasets, respectively. Furthermore, TCAN outperforms other representative baselines by 10.4%, 3.8%, and 10.4% in terms of MSLE, MAE, and R-squared on average while maintaining good interpretability.