Less is More: Unseen Domain Fake News Detection via Causal Propagation Substructures

TL;DR

This paper presents CSDA, a causal substructure-based model that improves zero-shot and few-shot fake news detection on unseen domains by extracting and leveraging causal propagation subgraphs.

Contribution

The introduction of a graph neural network-based causal substructure extraction method for domain adaptive fake news detection, enhancing OOD generalization and few-shot learning capabilities.

Findings

CSDA outperforms state-of-the-art models by 7-16% in accuracy on OOD datasets.

Causal substructure extraction improves detection robustness in unseen domains.

Contrastive learning further boosts performance in few-shot scenarios.

Abstract

The spread of fake news on social media poses significant threats to individuals and society. Text-based and graph-based models have been employed for fake news detection by analysing news content and propagation networks, showing promising results in specific scenarios. However, these data-driven models heavily rely on pre-existing in-distribution data for training, limiting their performance when confronted with fake news from emerging or previously unseen domains, known as out-of-distribution (OOD) data. Tackling OOD fake news is a challenging yet critical task. In this paper, we introduce the Causal Subgraph-oriented Domain Adaptive Fake News Detection (CSDA) model, designed to enhance zero-shot fake news detection by extracting causal substructures from propagation graphs using in-distribution data and generalising this approach to OOD data. The model employs a graph neural network based mask generation process to identify dominant nodes and edges within the propagation graph, using these substructures for fake news detection. Additionally, the performance of CSDA is further improved through contrastive learning in few-shot scenarios, where a limited amount of OOD data is available for training. Extensive experiments on public social media datasets demonstrate that CSDA effectively handles OOD fake news detection, achieving a 7 to 16 percents accuracy improvement over other state-of-the-art models.