Predicting the popularity of online content is an important task for content recommendation, social influence prediction and so on. Recent deep learning models generally utilize graph neural networks to model the complex relationship between information cascade graph and future popularity, and have shown better prediction results compared with traditional methods. However, existing models adopt simple graph pooling strategies, e.g., summation or average, which prone to generate inefficient cascade graph representation and lead to unsatisfactory prediction results. Meanwhile, they often overlook the temporal information in the diffusion process which has been proved to be a salient predictor for popularity prediction. To focus attention on the important users and exclude noises caused by other less relevant users when generating cascade graph representation, we learn the importance coefficient of users and adopt sample mechanism in graph pooling process. In order to capture the temporal features in the diffusion process, we incorporate the inter-infection duration time information into our model by using LSTM neural network. The results show that temporal information rather than cascade graph information is a better predictor for popularity. The experimental results on real datasets show that our model significantly improves the prediction accuracy compared with other state-of-the-art methods.

Modeling and predicting the information diffusion process on social platforms is a critical task in many real-world applications. Recent studies generally model the diffusion graph using graph neural networks to capture the implicit dependencies among users. However, existing studies construct the diffusion graph in a way which cannot fully describe the global dependencies of users due to their narrow definition of user relationship. Meanwhile, graph neural networks in these methods are not suitable for the social network scenario which has scarce node attributes. Therefore, we propose a novel diffusion graph construction method which can enhance relations among users and adopt a simplified graph convolutional operation which is suitable for diffusion prediction scenario. The learned user embedding in our model can effectively preserve the microscopic structure and the high-order proximities between users lies in both the social graph and diffusion graph. Experimental results on four real-world datasets show that the proposed model is superior to the most advanced information diffusion prediction methods.