Skip to content

Official PyTorch implementation of "AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection" [to be announced]

Notifications You must be signed in to change notification settings

mala-lab/AnomalyGFM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

34 Commits
 
 

Repository files navigation

AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection

1️⃣ AnomalyGFM is the first GAD-oriented GFM with strong zero-shot and few-shot generalization abilities.

2️⃣ A comprehensive benchmark on both zero-shot and few-shot settings using 11 real-world GAD datasets is established, on which i) AnomalyGFM performs significantly better the state-of-the-art unsupervised, supervised, and generalist GAD methods, and ii) AnomalyGFM can scale up to very large graphs

The GAD datasets after feature alignment can be obtained from google drive link.

The code for AnomalyGFM and the adaptation to the baseline will be uploaded soon.

About

Official PyTorch implementation of "AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection" [to be announced]

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published