A Macro- and Micro-Hierarchical Transfer Learning Framework for Cross-Domain Fake News Detection

2025-02-20

AI Summary

Cross-domain fake news detection suffers from domain shift, which undermines knowledge transfer: microscopically, authenticity-irrelevant features interfere with shared feature transfer; macroscopically, cross-domain commonalities in user behavior and news content remain unmodeled. To address this, we propose a macro-micro dual-level transfer framework. At the micro level, feature disentanglement separates authenticity-relevant and authenticity-irrelevant representations; at the macro level, shared behavioral patterns of cross-domain common users are explicitly modeled to enhance transfer robustness. The framework integrates adversarial training with multi-task joint optimization. Extensive experiments on multiple real-world datasets demonstrate significant improvements over state-of-the-art methods, achieving average cross-domain accuracy gains of 4.2–7.8 percentage points. Notably, our approach is the first to enable user-behavior-guided, hierarchical, and controllable feature transfer for fake news detection.

Technology Category

• Application Domains: Misinformation & Fake News
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Cross-domain fake news detection aims to mitigate domain shift and improve detection performance by transferring knowledge across domains. Existing approaches transfer knowledge based on news content and user engagements from a source domain to a target domain. However, these approaches face two main limitations, hindering effective knowledge transfer and optimal fake news detection performance. Firstly, from a micro perspective, they neglect the negative impact of veracity-irrelevant features in news content when transferring domain-shared features across domains. Secondly, from a macro perspective, existing approaches ignore the relationship between user engagement and news content, which reveals shared behaviors of common users across domains and can facilitate more effective knowledge transfer. To address these limitations, we propose a novel macro- and micro- hierarchical transfer learning framework (MMHT) for cross-domain fake news detection. Firstly, we propose a micro-hierarchical disentangling module to disentangle veracity-relevant and veracity-irrelevant features from news content in the source domain for improving fake news detection performance in the target domain. Secondly, we propose a macro-hierarchical transfer learning module to generate engagement features based on common users' shared behaviors in different domains for improving effectiveness of knowledge transfer. Extensive experiments on real-world datasets demonstrate that our framework significantly outperforms the state-of-the-art baselines.

Problem

• Addresses cross-domain fake news detection limitations.
• Improves knowledge transfer via veracity-relevant features.
• Enhances detection with user engagement and content analysis.

Innovation

• Hierarchical transfer learning framework
• Disentangling veracity-relevant features
• Generating engagement features