jayaram-r / domain-adaptation-autoencoder

Public repository for the ICLR'23 paper "Few-shot domain adaptation for end-to-end communication"

Few-Shot Domain Adaptation For End-to-End Communication

This repository is the official implementation for our ICLR 2023 Spotlight paper:

Few-Shot Domain Adaptation For End-to-End Communication

Jayaram Raghuram, Yijing Zeng, Dolores Garcia Marti, Rafael Ruiz Ortiz, Somesh Jha, 
Joerg Widmer, Suman Banerjee

OpenReview link: https://openreview.net/forum?id=-i0yq60xf8

Arxiv link: https://arxiv.org/abs/2108.00874

Requirements

The code has been tested on a Ubuntu 18.04 Linux server and a Python 3.7.12 environment. A Conda environment was created with the following packages:

• numpy - 1.21.5
• scipy - 1.7.3
• tensorflow - 2.7.0
• tensorflow-probability - 0.15.0
• scikit-learn - 1.0.2
• matplotlib - 3.5.1
• jupyter - 1.0.0

Citation

Please cite our work if you use the codebase:

@inproceedings{
raghuram2023fewshot,
title={Few-Shot Domain Adaptation For End-to-End Communication},
author={Jayaram Raghuram and Yijing Zeng and Dolores Garcia Marti and Rafael Ruiz Ortiz and Somesh Jha and Joerg Widmer and Suman Banerjee},
booktitle={International Conference on Learning Representations},
year={2023},
url={https://openreview.net/forum?id=-i0yq60xf8}
}

License

Please refer to the LICENSE.