DGFraud and DGFraud-TF2
These are ecosystem siblings—DGFraud-TF2 is a TensorFlow 2.x reimplementation of the original DGFraud framework, offering the same graph-based fraud detection functionality in a modernized deep learning backend rather than a competing alternative.
About DGFraud
safe-graph/DGFraud
A Deep Graph-based Toolbox for Fraud Detection
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.
About DGFraud-TF2
safe-graph/DGFraud-TF2
A Deep Graph-based Toolbox for Fraud Detection in TensorFlow 2.X
Scores updated daily from GitHub, PyPI, and npm data. How scores work