safe-graph/DGFraud-TF2

Introduction | Useful Resources | Installation | Datasets | User Guide | Implemented Models | How to Contribute

DGFraud-TF2 is a Graph Neural Network (GNN) based toolbox for fraud detection. It is the Tensorflow 2.X version of DGFraud, which is implemented using TF 1.X. It integrates the implementation & comparison of state-of-the-art GNN-based fraud detection models. The introduction of implemented models can be found here.

We welcome contributions to this repo like adding new fraud detectors and extending the features of the toolbox.

If you use the toolbox in your project, please cite the paper below and the algorithms you used:

CIKM'20 (PDF)

@inproceedings{dou2020enhancing,
  title={Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters},
  author={Dou, Yingtong and Liu, Zhiwei and Sun, Li and Deng, Yutong and Peng, Hao and Yu, Philip S},
  booktitle={Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM'20)},
  year={2020}
}

• PyGOD: A Python Library for Graph Outlier Detection (Anomaly Detection)
• UGFraud: An Unsupervised Graph-based Toolbox for Fraud Detection
• Graph-based Fraud Detection Paper List
• Awesome Fraud Detection Papers
• PyOD: A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)
• PyODD: An End-to-end Outlier Detection System
• DGL: Deep Graph Library
• Realtime Fraud Detection with GNN on DGL
• Outlier Detection DataSets (ODDS)

git clone https://.com/safe-graph/DGFraud-TF2.git
cd DGFraud-TF2
python setup.py install

* python>=3.6
* tensorflow>=2.0
* numpy>=1.16.4
* scipy>=1.2.0

We uses the pre-processed DBLP dataset from Jhy1993/HAN You can run the FdGars, Player2Vec, GeniePath and GEM based on the DBLP dataset. Unzip the archive before using the dataset:

cd dataset
unzip DBLP4057_GAT_with_idx_tra200_val_800.zip

We implement example graphs for SemiGNN, GAS and GEM in data_loader.py. Because those models require unique graph structures or node types, which cannot be found in opensource datasets.

For GraphConsis and GraphSAGE, we preprocessed Yelp Spam Review Dataset with reviews as nodes and three relations as edges.

The dataset with .mat format is located at /dataset/YelpChi.zip. The .mat file includes:

• net_rur, net_rtr, net_rsr: three sparse matrices representing three homo-graphs defined in GraphConsis paper;
• features: a sparse matrix of 32-dimension handcrafted features;
• label: a numpy array with the ground truth of nodes. 1 represents spam and 0 represents benign.

The YelpChi data preprocessing details can be found in our CIKM'20 paper. To get the complete metadata of the Yelp dataset, please email to [email protected] for inquiry.

You can find the implemented models in algorithms directory. For example, you can run Player2Vec using:

python Player2Vec_main.py 

You can specify parameters for models when running the code.

Have a look at the load_data_dblp() function in utils/utils.py for an example.

In order to use your own data, you have to provide:

• adjacency matrices or adjlists (for GAS);
• a feature matrix
• a label matrix then split feature matrix and label matrix into testing data and training data.

You can specify a dataset as follows:

python xx_main.py --dataset your_dataset 

or by editing xx_main.py

The repository is organized as follows:

• algorithms/ contains the implemented models and the corresponding example code;
• layers/ contains all GNN layers used by implemented models;
• dataset/ contains the necessary dataset files;
• utils/ contains:
  • loading and splitting the data (data_loader.py);
  • contains various utilities (utils.py).

You are welcomed to contribute to this open-source toolbox. Currently, you can create PR or email to [email protected] for inquiry.