CCasGNN: Collaborative Cascade Prediction Based on Graph Neural Networks
This work addresses cascade prediction for social network analysis, offering an incremental improvement over existing methods by combining features more effectively.
The paper tackles the problem of cascade prediction by modeling information diffusion, proposing a novel method that integrates individual profile, structural features, and sequence information, and reports significant improvements in prediction accuracy on two real-world datasets compared to state-of-the-art approaches.
Cascade prediction aims at modeling information diffusion in the network. Most previous methods concentrate on mining either structural or sequential features from the network and the propagation path. Recent efforts devoted to combining network structure and sequence features by graph neural networks and recurrent neural networks. Nevertheless, the limitation of spectral or spatial methods restricts the improvement of prediction performance. Moreover, recurrent neural networks are time-consuming and computation-expensive, which causes the inefficiency of prediction. Here, we propose a novel method CCasGNN considering the individual profile, structural features, and sequence information. The method benefits from using a collaborative framework of GAT and GCN and stacking positional encoding into the layers of graph neural networks, which is different from all existing ones and demonstrates good performance. The experiments conducted on two real-world datasets confirm that our method significantly improves the prediction accuracy compared to state-of-the-art approaches. What's more, the ablation study investigates the contribution of each component in our method.