Bias Mitigation Framework for Intersectional Subgroups in Neural Networks

Narine Kokhlikyan, Bilal Alsallakh, Fulton Wang, Vivek Miglani, Aobo Yang, David Adkins

Keywords: Fairness, Feature Interactions, Bias Mitigation

TL;DR: This papers proposes a bias mitigation approach for intersectional subgroups.

Abstract: We propose a fairness-aware learning framework that mitigates intersectional subgroup bias associated with protected attributes. Prior research has primarily focused on mitigating one kind of bias by incorporating complex fairness-driven constraints into optimization objectives or designing additional layers that focus on specific protected attributes. We introduce a simple and generic bias mitigation framework that prevents models from learning relationships between protected attributes and output variable by reducing mutual information. We demonstrate that our approach is effective in reducing bias with little or no drop in accuracy. We also show that our approach mitigates intersectional bias even when other attributes in the dataset are correlated with protected attributes. Finally, we validate our approach by studying feature interactions between protected and non-protected attributes. We demonstrate that these interactions are significantly reduced when applying our bias mitigation.

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: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)