Journal
AIES '19: PROCEEDINGS OF THE 2019 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY
Volume -, Issue -, Pages 247-254Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3306618.3314287
Keywords
fairness; discrimination; machine learning; post-processing
Categories
Funding
- Google Faculty Research Award
- NSF [CCF-1763299]
Ask authors/readers for more resources
Machine learning predictors are successfully deployed in applications ranging from disease diagnosis, to predicting credit scores, to image recognition. Even when the overall accuracy is high, the predictions often have systematic biases that harm specific subgroups, especially for subgroups that are minorities in the training data. We develop a rigorous framework of multiaccuracy auditing and post-processing to improve predictor accuracy across identifiable subgroups. Our algorithm, MULTIACCURACY BOOST, works in any setting where we have black-box access to a predictor and a relatively small set of labeled data for auditing. We prove guarantees on the convergence rate of the algorithm and show that it improves overall accuracy at each step. Importantly, if the initial model is accurate on an identifiable subgroup, then the post-processed model will be also. We demonstrate the effectiveness of this approach on diverse applications in image classification, finance, and population health. MULTIACCURACY BOOST can improve subpopulation accuracy (e.g. for black women) even when the sensitive features (e.g. race, gender) are not known to the algorithm.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available