Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection

Abstract

Rumor detection on social media has become increasingly important. Most existing graph-based models presume rumor propagation trees (RPTs) have deep structures and learn sequential stance features along branches. However, through statistical analysis on real-world datasets, we find RPTs exhibit wide structures, with most nodes being shallow 1-level replies. To focus learning on intensive substructures, we propose Rumor Adaptive Graph Contrastive Learning (RAGCL) method with adaptive view augmentation guided by node centralities. We summarize three principles for RPT augmentation: 1) exempt root nodes, 2) retain deep reply nodes, 3) preserve lower-level nodes in deep sections. We employ node dropping, attribute masking and edge dropping with probabilities from centrality-based importance scores to generate views. A graph contrastive objective then learns robust rumor representations. Extensive experiments on four benchmark datasets demonstrate RAGCL outperforms state-of-the-art methods. Our work reveals the wide-structure nature of RPTs and contributes an effective graph contrastive learning approach tailored for rumor detection through principled adaptive augmentation. The proposed principles and augmentation techniques can potentially benefit other applications involving tree-structured graphs.

This paper is accepted by AAAI2024

References in corpus (15)

• A Simple Framework for Contrastive Learning of Visual Representations
• Neural Message Passing for Quantum Chemistry
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Graph Contrastive Learning with Adaptive Augmentation
• Momentum Contrast for Unsupervised Visual Representation Learning
• Graph Contrastive Learning with Augmentations
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Contrastive Multi-View Representation Learning on Graphs
• Neural Relational Inference for Interacting Systems
• Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
• A Note on Over-Smoothing for Graph Neural Networks
• Graph Contrastive Learning Automated
• AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
• DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization

Cited by in corpus (1)

• Rumor Detection on Social Media with Reinforcement Learning-based Key Propagation Graph Generator