Graph-COM/GAD-NR

[WSDM 2024] GAD-NR : Graph Anomaly Detection via Neighborhood Reconstruction

21
/ 100
Experimental

This project helps detect unusual or suspicious activity within network-like data, such as social connections, transaction histories, or computer network logs. By analyzing the structure and attributes of each connection and node, it identifies individual nodes that behave differently from their neighbors or the overall network pattern. This is ideal for security analysts, fraud investigators, or social media platform managers who need to pinpoint anomalies in complex, interconnected data.

No commits in the last 6 months.

Use this if you need to reliably find various types of unusual nodes—whether they have strange features, form odd connections, or both—within large datasets that can be represented as graphs.

Not ideal if your data is not inherently connected or graph-structured, or if you are looking for anomalies based purely on individual data points without considering their relationships.

network-security fraud-detection social-media-spam anomaly-detection graph-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

56

Forks

2

Language

Jupyter Notebook

License

Last pushed

Nov 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Graph-COM/GAD-NR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.