Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes
Yusuke Hirota, Jerone Andrews, Dora Zhao, Orestis Papakyriakopoulos, Apostolos Modas, Yuta Nakashima, Alice Xiang
Abstract
We tackle societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Traditional methods only target labeled attributes, ignoring biases from unlabeled ones. Using text-guided inpainting models, our approach ensures protected group independence from all attributes and mitigates inpainting biases through data filtering. Evaluations on multi-label image classification and image captioning tasks show our method effectively reduces bias without compromising performance across various models. Specifically, we achieve an average societal bias reduction of 46.1% in leakage-based bias metrics for multi-label classification and 74.8% for image captioning.
BibTeX
@inproceedings{hirota-etal-2024-resampled,
title = "Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes",
author = "Hirota, Yusuke and
Andrews, Jerone and
Zhao, Dora and
Papakyriakopoulos, Orestis and
Modas, Apostolos and
Nakashima, Yuta and
Xiang, Alice",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.471/",
doi = "10.18653/v1/2024.emnlp-main.471",
pages = "8249--8267"
}