Summary of Sefraud: Graph-based Self-explainable Fraud Detection Via Interpretative Mask Learning, by Kaidi Li et al.
SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning
by Kaidi Li, Tianmeng Yang, Min Zhou, Jiahao Meng, Shendi Wang, Yihui Wu, Boshuai Tan, Hu Song, Lujia Pan, Fan Yu, Zhenli Sheng, Yunhai Tong
First submitted to arxiv on: 17 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 proposes a novel graph-based self-explainable fraud detection framework called SEFraud, designed to simultaneously detect fraud and provide interpretable results. The approach leverages customized heterogeneous graph transformer networks with learnable feature masks and edge masks to learn expressive representations from informative heterogeneously typed transactions. A new triplet loss is designed to enhance the performance of mask learning. Experimental results demonstrate SEFraud’s effectiveness in both fraud detection performance and interpretability, outperforming previous methods on various datasets. Moreover, SEFraud has been deployed at ICBC, providing accurate detection results and comprehensive explanations that align with expert business understanding. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Fraud detection is important for industries like banks and e-commerce. This paper introduces a new way to detect fraud while also explaining why it thinks something is fraudulent. Current methods can’t explain their decisions, but SEFraud can. It uses special computer networks and learning techniques to understand complex transactions. Tests show that SEFraud works well and can be used in real-world situations. |
Keywords
* Artificial intelligence * Mask * Transformer * Triplet loss
