EleMisi / VAEL

Codebase for VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming

VAEL

Codebase for VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming.

If you use this codebase, please cite:

@misc{https://doi.org/10.48550/arxiv.2202.04178,
  doi = {10.48550/ARXIV.2202.04178},
  url = {https://arxiv.org/abs/2202.04178},
  author = {Misino, Eleonora and Marra, Giuseppe and Sansone, Emanuele},
  keywords = {Programming Languages (cs.PL), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

Prerequisites

• Python >=3.7
• Dependencies:

  pip install -r requirements.txt

  Note: if something goes wrong with PySDD, try pip install -vvv --upgrade --force-reinstall --no-binary :all: --no-deps pysdd

Usage

1. Clone the repo

   git clone https://github.com/EleMisi/VAEL.git

2. Install the dependencies

   pip install -r requirements.txt

3. Set the experiment(s) configuration in file config.py

4. Run the experiment(s)

   python run_VAEL.py

   Use flag --task mnist to run 2digit MNIST experiment(s), and --task mario to run Mario experiment(s).

Results

The results are stored in the folder ./<exp_folder>/<exp_class>/ specified in run_VAEL.py.

In particular:

• the resulting metrics for each tested configuration are reported in exp_class.csv
• each subfolder refers to a specific configuration and contains
  • the model checkpoint
  • the learning curves
  • some samples of image reconstruction and generation

Author

• Eleonora Misino - [e-mail]
• Giuseppe Marra - [e-mail]
• Emanuele Sansone - [e-mail]