Hierarchical Information Enhancement Network for Cascade Prediction in Social Networks
This addresses the challenge of cascade prediction for social network analysis, though it appears incremental by combining existing techniques like DeepWalk and graph convolutional networks.
The paper tackles the problem of predicting information cascades in social networks by proposing HIENet, which integrates cascade sequences, user social graphs, and sub-cascade graphs into a unified framework, achieving improved predictive performance as demonstrated in extensive experiments.
Understanding information cascades in networks is a fundamental issue in numerous applications. Current researches often sample cascade information into several independent paths or subgraphs to learn a simple cascade representation. However, these approaches fail to exploit the hierarchical semantic associations between different modalities, limiting their predictive performance. In this work, we propose a novel Hierarchical Information Enhancement Network (HIENet) for cascade prediction. Our approach integrates fundamental cascade sequence, user social graphs, and sub-cascade graph into a unified framework. Specifically, HIENet utilizes DeepWalk to sample cascades information into a series of sequences. It then gathers path information between users to extract the social relationships of propagators. Additionally, we employ a time-stamped graph convolutional network to aggregate sub-cascade graph information effectively. Ultimately, we introduce a Multi-modal Cascade Transformer to powerfully fuse these clues, providing a comprehensive understanding of cascading process. Extensive experiments have demonstrated the effectiveness of the proposed method.