Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference

Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference in Pytorch

Hierarchical Input	Latent Output

How to run

Requirements

NumPy
PyTorch 1.6
Scipy
networkx
json

pip install -r requirements.txt

Installing

Clone the repository:

$ git clone https://github.com/AliLotfi92/ESI_HGE
$ cd esihge

Install requirements:
```
$ pip install -r requirements.txt
```

Arguments:

lr: learning rate for the inference network
dropout: Dropout rate (1 - keep probability).
epochs: number of epochs to train the model.
c: constant negative curvature
K: semi-implicit vi hyperparameters
J: semi-implicit vi hyperparameters
dataset-str: synthetic, cora, citeseer, or pubmed

Results:

Latent codes discoveries