This codebase implements the method from Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment..

This codebase is a re-implementation and was not the one used for generating the experiment results in the paper.

Please refer to scripts/*.sh for running experiments on a toy example and handwritten digit datasets.

The code works with Python>=3.6 and PyTorch>=1.0.

If you use this codebase for your research, please cite the paper:

@inproceedings{wu2019domain,
  title={Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment},
  author={Wu, Yifan and Winston, Ezra and Kaushik, Divyansh and Lipton, Zachary},
  booktitle={International Conference on Machine Learning},
  pages={6872--6881},
  year={2019}
}