GraPHmax: Datasets: There is a folder graphdatasets that contains all the required datasets. How to run: Use the following command to run GraPHmax with default values of the parameters on MUTAG dataset. python main.py Requirements: Install python in your system. Requirements file has been given in the model folder. To install the same libraries run pip install -r requirements.txt These are python libraries that are required to run the code.

1. Tensorflow (version: 1.14.0) with python 3.6.9.
2. Networkx (version: 2.3)
3. matplotlib
4. pandas
5. keras
6. scipy
7. pickle
8. collections Hyperparameters Settings: There are some hyperparameters one can change during execution.
9. plrt : Pooling ratio
10. plly : Number of Pooling layers
11. emb : Embedding dimenion
12. lrp : Learning rate for periphery representation
13. lrh : Learning rate for hierarchical representation
14. lrl : Learning rate for classification task
15. dropout : Dropout rate
16. negpr : Number of negative samples for periphery discriminator
17. neghr: Number of negative samples hierarchical discriminator
18. dataset: Name of the dataset to perform classification on.

One can specify these hyperparameters during running the code. python main.py --dataset MUTAG