Summary of Fanfold: Graph Normalizing Flows-driven Asymmetric Network For Unsupervised Graph-level Anomaly Detection, by Rui Cao et al.
FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detection
by Rui Cao, Shijie Xue, Jindong Li, Qi Wang, Yi Chang
First submitted to arxiv on: 29 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 approach for unsupervised graph-level anomaly detection, addressing the limitations of existing methods that rely on graph features. The proposed Graph Normalizing Flows-driven Asymmetric Network For Unsupervised Graph-Level Anomaly Detection (FANFOLD) uses knowledge distillation and normalizing flows to learn the underlying distribution of normal graphs, enabling the distinction between abnormal and normal graphs. The asymmetric network is trained using a source-target loss, achieving improved performance in detecting anomalies on 15 datasets from various fields. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us detect unusual patterns in complex networks without needing labeled data. It uses a new way to learn about normal patterns and then finds things that don’t fit those patterns. This can be useful for spotting problems or detecting changes in many types of networks, like social media or the internet. The approach is tested on 15 different datasets and outperforms other methods. |
Keywords
* Artificial intelligence * Anomaly detection * Knowledge distillation * Unsupervised
