Selecting or designing an appropriate domain adaptation algorithm for a given problem remains challenging. This paper presents a Transformer model that can provably approximate and opt for domain adaptation methods for a given dataset in the in-context learning framework, where a foundation model performs new tasks without updating its parameters at test time. Specifically, we prove that Transformers can approximate instance-based and feature-based unsupervised domain adaptation algorithms and automatically select an algorithm suited for a given dataset. Numerical results indicate that in-context learning demonstrates an adaptive domain adaptation surpassing existing methods.
@article{arxiv.2405.16819,
title = {Automatic Domain Adaptation by Transformers in In-Context Learning},
author = {Ryuichiro Hataya and Kota Matsui and Masaaki Imaizumi},
journal= {arXiv preprint arXiv:2405.16819},
year = {2024}
}