When does Bias Transfer in Transfer Learning?
Abstract
Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. In this work, we demonstrate that there can exist a downside after all: bias transfer, or the tendency for biases of the source model to persist even after adapting the model to the target class. Through a combination of synthetic and natural experiments, we show that bias transfer both (a) arises in realistic settings (such as when pre-training on ImageNet or other standard datasets) and (b) can occur even when the target dataset is explicitly de-biased. As transfer-learned models are increasingly deployed in the real world, our work highlights the importance of understanding the limitations of pre-trained source models. Code is available at https://github.com/MadryLab/bias-transfer
Cite
@article{arxiv.2207.02842,
title = {When does Bias Transfer in Transfer Learning?},
author = {Hadi Salman and Saachi Jain and Andrew Ilyas and Logan Engstrom and Eric Wong and Aleksander Madry},
journal= {arXiv preprint arXiv:2207.02842},
year = {2022}
}