Summary of Generative Semi-supervised Graph Anomaly Detection, by Hezhe Qiao et al.
Generative Semi-supervised Graph Anomaly Detection
by Hezhe Qiao, Qingsong Wen, Xiaoli Li, Ee-Peng Lim, Guansong Pang
First submitted to arxiv on: 19 Feb 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 explores semi-supervised graph anomaly detection (GAD), where a portion of nodes in a graph are known to be normal. Existing methods can benefit from these normal nodes, but their utilization is limited. The authors propose a novel Generative GAD approach called GGAD, which generates pseudo anomaly nodes (outlier nodes) for training a one-class classifier. GGAD leverages two priors about anomaly nodes: asymmetric local affinity and egocentric closeness. Experimental results on six real-world datasets demonstrate that GGAD outperforms state-of-the-art unsupervised and semi-supervised GAD methods, with varying numbers of training normal nodes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using special types of computer networks called graphs to find unusual patterns or “anomalies” in the data. Normally, we have to analyze all the data without knowing which parts are normal, but this paper shows that if we know a little bit about what’s normal, it can actually help us detect anomalies better! The authors came up with a new way to use this information, called Generative GAD (GGAD), and tested it on different datasets. GGAD worked really well and was better than other methods at finding anomalies. |
Keywords
* Artificial intelligence * Anomaly detection * Semi supervised * Unsupervised
