Summary of Enhancing Fairness in Unsupervised Graph Anomaly Detection Through Disentanglement, by Wenjing Chang et al.
Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement
by Wenjing Chang, Kay Liu, Philip S. Yu, Jianjun Yu
First submitted to arxiv on: 3 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computers and Society (cs.CY); 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 The paper proposes a novel framework for graph anomaly detection (GAD) that integrates fairness and utility, addressing the critical gap in current GAD methods. The authors introduce DisEntangle-based FairnEss-aware aNomaly Detection (DEFEND), which disentangles informative node representations from sensitive attributes using graph neural networks (GNNs). DEFEND also employs reconstruction-based anomaly detection, focusing on node attributes without incorporating graph structure, and constrains the correlation between the reconstruction error and predicted sensitive attributes. Experimental results on real-world datasets show that DEFEND effectively performs GAD and enhances fairness compared to state-of-the-art baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper aims to make graph anomaly detection (GAD) fairer by integrating fairness with utility. Right now, most GAD methods are biased and might not be suitable for real-world use due to societal and ethical restrictions. The authors propose a new method called DEFEND that uses special techniques to reduce bias in the way nodes are represented in graphs. They also use another technique to detect anomalies without considering the graph structure. This helps ensure that the method is fairer than existing methods. In experiments, the authors found that their method works well and is more fair. |
Keywords
» Artificial intelligence » Anomaly detection
