safe-graph/DGFraud

A Deep Graph-based Toolbox for Fraud Detection

51
/ 100
Established

Implements multiple GNN architectures (SemiGNN, GAS, FdGars, GeniePath, GEM) for comparative evaluation on fraud detection tasks, with support for heterogeneous graphs and multi-relational data structures. Built on TensorFlow with modular base models enabling custom dataset integration through adjacency matrices, feature matrices, and labels. Targets domains like financial fraud, spam reviews, and malicious account detection across DBLP, Yelp, and custom graph datasets.

750 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

750

Forks

165

Language

Python

License

Apache-2.0

Last pushed

Apr 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/safe-graph/DGFraud"

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