Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure
Name
AIES_2019_Algorithmic_Bias.pdf
Description
Main article
Size
3.53 MB
Format
Adobe PDF
Checksum (MD5)
3df8903c03a1ceaf90e9fb1c10b00da3
Author(s)
Soleimany, Ava
Amini, Alexander A
Schwarting, Wilko
Bhatia, Sangeeta N
Rus, Daniela L
Date Issued
January 2019
Journal
Proceedings of the 2019 AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES)
Publisher
AAAI/ACM
Citation
Amini, Alexander et al. "Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure." Proceedings of the 2019 AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 27-28 January, 2019, Honolulu, Hawaii, United States, AAAI/ACM, 2019.
Version
Author's final manuscript
Abstract
Recent research has highlighted the vulnerabilities of modern machine learning based systems to bias, especially for segments of society that are under-represented in training data. In this work, we develop a novel, tunable algorithm for mitigating the hidden, and potentially unknown, biases within training data. Our algorithm fuses the original learning task with a
variational autoencoder to learn the latent structure within the dataset and then adaptively uses the learned latent distributions to re-weight the importance of certain data points while training. While our method is generalizable across various data modalities and learning tasks, in this work we use our algorithm to address the issue of racial and gender bias in facial
detection systems. We evaluate our algorithm on the Pilot Parliaments Benchmark (PPB), a dataset specifically designed to evaluate biases in computer vision systems, and demonstrate increased overall performance as well as decreased categorical bias with our debiasing approach.
MIT Department
Harvard University--MIT Division of Health Sciences and Technology
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://www.aies-conference.com/wp-content/papers/main/AIES-19_paper_220.pdf
