Estimating Causal Effect by Deep Encoding Generative Modeling. CausalEGM utilizes deep generative neural newtworks for estimating the causal effect by decoupling the high-dimensional confounder into a set of different latent variables with specific dependency on treatment or potential outcome.

• TensorFlow>=2.4.1
• Python>=3.6.1

CausalEGM can be installed by

pip install CausalEGM

Note that a GPU is recommended for accelerating the model training. However, GPU is not a must, CausalEGM can be installed on any personal computer (e.g, Macbook) or computational cluster.

This section provides instructions on how to reproduce results in the our paper.

We provide the config files for all the datasets used in our study. These config files can be found in configs folder.

cd src
python3 main.py -c CONFIG_PATH

Please feel free to open an issue in Github or contact [email protected] if you have any problem in CausalEGM.

If you find CausalEGM useful for your work, please consider citing our paper:

Qiao Liu, Zhongren Chen, Wing Hung Wong. CausalEGM: a general causal inference framework by encoding generative modeling[J]. arXiv preprint arXiv:2212.05925, 2022.

This project is licensed under the MIT License - see the LICENSE.md file for details