Graph Neural Networks with Continual Learning for Fake News Detection from Social Media

Abstract

Although significant effort has been applied to fact-checking, the prevalence of fake news over social media, which has profound impact on justice, public trust and our society, remains a serious problem. In this work, we focus on propagation-based fake news detection, as recent studies have demonstrated that fake news and real news spread differently online. Specifically, considering the capability of graph neural networks (GNNs) in dealing with non-Euclidean data, we use GNNs to differentiate between the propagation patterns of fake and real news on social media. In particular, we concentrate on two questions: (1) Without relying on any text information, e.g., tweet content, replies and user descriptions, how accurately can GNNs identify fake news? Machine learning models are known to be vulnerable to adversarial attacks, and avoiding the dependence on text-based features can make the model less susceptible to the manipulation of advanced fake news fabricators. (2) How to deal with new, unseen data? In other words, how does a GNN trained on a given dataset perform on a new and potentially vastly different dataset? If it achieves unsatisfactory performance, how do we solve the problem without re-training the model on the entire data from scratch? We study the above questions on two datasets with thousands of labelled news items, and our results show that: (1) GNNs can achieve comparable or superior performance without any text information to state-of-the-art methods. (2) GNNs trained on a given dataset may perform poorly on new, unseen data, and direct incremental training cannot solve the problem---this issue has not been addressed in the previous work that applies GNNs for fake news detection. In order to solve the problem, we propose a method that achieves balanced performance on both existing and new datasets, by using techniques from continual learning to train GNNs incrementally.

arXiv comment9 pages, 7 figures, 2 tables

References in corpus (17)

• Explaining and Harnessing Adversarial Examples
• Semi-Supervised Classification with Graph Convolutional Networks
• Overcoming catastrophic forgetting in neural networks
• Intriguing properties of neural networks
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• A Review of Relational Machine Learning for Knowledge Graphs
• Computational fact checking from knowledge networks
• TI-CNN: Convolutional Neural Networks for Fake News Detection
• FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media
• Fake News Detection on Social Media using Geometric Deep Learning
• Some Like it Hoax: Automated Fake News Detection in Social Networks
• FAKEDETECTOR: Effective Fake News Detection with Deep Diffusive Neural Network
• DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning
• A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples
• Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks
• Network-based Fake News Detection: A Pattern-driven Approach

Cited by in corpus (8)

• Graph-based Modeling of Online Communities for Fake News Detection
• Research Status of Deep Learning Methods for Rumor Detection
• Fake News Detection in Social Media using Graph Neural Networks and NLP Techniques: A COVID-19 Use-case
• Addressing contingency in algorithmic (mis)information classification: Toward a responsible machine learning agenda
• Unified Question Generation with Continual Lifelong Learning
• Knowledge Enhanced Multi-modal Fake News Detection
• User Preference-aware Fake News Detection
• A Review of Web Infodemic Analysis and Detection Trends across Multi-modalities using Deep Neural Networks