https://github.com/paccmann/paccmann_polymer
Graph-regularized VAE and the impact of topology on learned representations
https://github.com/paccmann/paccmann_polymer
deep-learning gnn graph-regularized-vae manifold-learning pytorch vae
Last synced: about 2 months ago
JSON representation
Graph-regularized VAE and the impact of topology on learned representations
- Host: GitHub
- URL: https://github.com/paccmann/paccmann_polymer
- Owner: PaccMann
- License: mit
- Created: 2020-10-06T09:36:17.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2021-09-17T22:22:34.000Z (about 4 years ago)
- Last Synced: 2025-02-02T17:21:50.203Z (8 months ago)
- Topics: deep-learning, gnn, graph-regularized-vae, manifold-learning, pytorch, vae
- Language: Python
- Homepage:
- Size: 77.1 KB
- Stars: 2
- Watchers: 6
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://github.com/PaccMann/paccmann_polymer/actions/workflows/build.yml)
# paccmann_polymer
PyTorch implementation of `paccmann_polymer`. Repo for the paper:
*On the Importance of Looking at the Manifold*.
## Requirements
- `conda>=3.7`
## Installation
The library itself has few dependencies (see [setup.py](setup.py)) with loose requirements.
Create a conda environment:
```console
conda env create -f conda.yml
```
Activate the environment:
```console
conda activate paccmann_polymer
```
Install in editable mode for development:
```console
pip install -e .
```
Install a kernel for the newly created environment:
```console
ipython kernel install --name "paccmann_polymer"
```
## Experiments
To reproduce the experiments from the paper, check
`paccmann_polymer/topologically_regularized_models/experiments`.