When does Bias Transfer in Transfer Learning?

Hadi Salman, Saachi Jain, Andrew Ilyas, Logan Engstrom, Eric Wong, Aleksander Madry

Keywords: transfer learning, bias

TL;DR: We study a potential vulnerability of transfer learning where biases and other vulnerabilities from the source dataset remain present in downstream models.

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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2207.02842/code)