Source code for TNNLS2023 "TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Nature"
- Python3.7
- NumPy
- SciPy
- PyTorch
- DGL
- scikit-learn
Before running the code, please unzip the dataset.zip and make a directory named checkpoint.
- `python run.py --dataset advogato
Please refer to the args.py for more parameters.
If you make advantage of TrustGNN in your research, please cite the following in your manuscript:
Cuiying Huo, Dongxiao He, Chundong Liang, Di Jin, Tie Qiu and Lingfei Wu, "TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Nature", IEEE Trans. Neural Netw. Learn. Syst., 2023.