Summary of Loss-gat: Label Propagation and One-class Semi-supervised Graph Attention Network For Fake News Detection, by Batool Lakzaei and Mostafa Haghir Chehreghani and Alireza Bagheri
LOSS-GAT: Label Propagation and One-Class Semi-Supervised Graph Attention Network for Fake News Detection
by Batool Lakzaei, Mostafa Haghir Chehreghani, Alireza Bagheri
First submitted to arxiv on: 13 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles the pressing issue of fake news detection in the era of social networks. Existing machine learning and deep learning approaches rely on large labeled datasets, which are often scarce. To address this challenge, the authors propose a graph-based model for data representation and introduce a semi-supervised, one-class approach called LOSS-GAT. The method employs Graph Neural Networks (GNNs) as an initial classifier to categorize news into fake and real categories. Structural augmentation techniques enhance the graph structure, allowing for more accurate predictions. The proposed method outperforms baseline models, including binary labeled models, on five common datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Fake news is a big problem that affects many people’s lives. Machine learning can help us detect fake news, but we need to use special tricks because most data isn’t labeled. This paper shows how to use graphs and special math to find fake news even when there aren’t many examples to learn from. The new method, called LOSS-GAT, is better than other methods that try to solve this problem. |
Keywords
* Artificial intelligence * Deep learning * Machine learning * Semi supervised
