Summary of A Graph Neural Architecture Search Approach For Identifying Bots in Social Media, by Georgios Tzoumanekas et al.
A Graph Neural Architecture Search Approach for Identifying Bots in Social Media
by Georgios Tzoumanekas, Michail Chatzianastasis, Loukas Ilias, George Kiokes, John Psarras, Dimitris Askounis
First submitted to arxiv on: 25 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 A novel Neural Architecture Search (NAS) technique is proposed to detect bots on social media platforms like X, Facebook, and Instagram. The approach, dubbed Deep and Flexible Graph Neural Architecture Search (DFG-NAS), leverages Relational Graph Convolutional Neural Networks (RGCNs) to construct a graph incorporating user relationships and metadata. DFG-NAS automatically searches for the optimal configuration of Propagation and Transformation functions in RGCNs, outperforming state-of-the-art models on the TwiBot-20 dataset with an accuracy of 85.7%. This work not only tackles bot detection but also advocates for broader NAS model implementation in neural network design automation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research uses special computer programs to help detect fake accounts on social media platforms like X, Facebook, and Instagram. Social media has millions of users daily, which can spread misinformation and hurt people’s lives. The scientists used a new way to design these computer programs, called Neural Architecture Search (NAS). They combined this with another technique, Relational Graph Convolutional Neural Networks (RGCNs), to make a better bot detector. They tested it on a big dataset of social media relationships and metadata, and it worked well, achieving an accuracy of 85.7%. |
Keywords
» Artificial intelligence » Neural network
