Adaptation Method for Misinformation Identification
Yangping Chen, Weijie Shi, Mengze Li, Yue Cui, Hao Chen, Jia Zhu, Jiajie Xu
TL;DR
ADOSE tackles cross-domain multimodal fake news detection by integrating a Modal-dependency Expertise Fusion Network with active sampling. It learns intra- and inter-modal deception patterns via three specialized classifiers, while selecting informative target samples through a Least-disagree Uncertainty Selector and ensuring diversity with a Multi-view Diversity Calculator. The training objective combines adversarial domain invariance, cross-modal alignment, and consensus among experts, enabling effective adaptation with limited target labels. On Pheme and Weibo, ADOSE consistently outperforms UDA/ADA baselines, demonstrating practical value for robust misinformation identification under domain shift.
Abstract
Multimodal fake news detection plays a crucial role in combating online misinformation. Unfortunately, effective detection methods rely on annotated labels and encounter significant performance degradation when domain shifts exist between training (source) and test (target) data. To address the problems, we propose ADOSE, an Active Domain Adaptation (ADA) framework for multimodal fake news detection which actively annotates a small subset of target samples to improve detection performance. To identify various deceptive patterns in cross-domain settings, we design multiple expert classifiers to learn dependencies across different modalities. These classifiers specifically target the distinct deception patterns exhibited in fake news, where two unimodal classifiers capture knowledge errors within individual modalities while one cross-modal classifier identifies semantic inconsistencies between text and images. To reduce annotation costs from the target domain, we propose a least-disagree uncertainty selector with a diversity calculator for selecting the most informative samples. The selector leverages prediction disagreement before and after perturbations by multiple classifiers as an indicator of uncertain samples, whose deceptive patterns deviate most from source domains. It further incorporates diversity scores derived from multi-view features to ensure the chosen samples achieve maximal coverage of target domain features. The extensive experiments on multiple datasets show that ADOSE outperforms existing ADA methods by 2.72\% $\sim$ 14.02\%, indicating the superiority of our model.