RaCMC: Residual-Aware Compensation Network with Multi-Granularity Constraints for Fake News Detection

TL;DR

RaCMC is a novel multimodal fake news detection method that enhances feature fusion and discrimination by using multi-scale residual compensation and multi-granularity constraints, leading to improved accuracy.

Contribution

The paper introduces RaCMC, a residual-aware network with multi-granularity constraints, for better cross-modal feature interaction and fake news classification.

Findings

Outperforms existing methods on Weibo17, Politifact, and GossipCop datasets.

Effectively amplifies differences between real and fake news.

Enhances feature fusion quality through multiscale residual modules.

Abstract

Multimodal fake news detection aims to automatically identify real or fake news, thereby mitigating the adverse effects caused by such misinformation. Although prevailing approaches have demonstrated their effectiveness, challenges persist in cross-modal feature fusion and refinement for classification. To address this, we present a residual-aware compensation network with multi-granularity constraints (RaCMC) for fake news detection, that aims to sufficiently interact and fuse cross-modal features while amplifying the differences between real and fake news. First, a multiscale residual-aware compensation module is designed to interact and fuse features at different scales, and ensure both the consistency and exclusivity of feature interaction, thus acquiring high-quality features. Second, a multi-granularity constraints module is implemented to limit the distribution of both the news overall and the image-text pairs within the news, thus amplifying the differences between real and fake news at the news and feature levels. Finally, a dominant feature fusion reasoning module is developed to comprehensively evaluate news authenticity from the perspectives of both consistency and inconsistency. Experiments on three public datasets, including Weibo17, Politifact and GossipCop, reveal the superiority of the proposed method.