CCasGNN: Collaborative Cascade Prediction Based on Graph Neural Networks

TL;DR

CCasGNN introduces a novel collaborative graph neural network framework combining GAT and GCN with positional encoding to improve cascade prediction accuracy in information diffusion modeling.

Contribution

The paper presents a new GNN-based method that integrates structural, sequential, and individual features with a collaborative framework and positional encoding, outperforming existing approaches.

Findings

Significant improvement in prediction accuracy over state-of-the-art methods

Effective integration of structural, sequential, and individual features

Ablation study confirms the contribution of each component

Abstract

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.