Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure

Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure

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...

Full description

Bibliographic Details
Main Authors: Soleimany, Ava (Author), Amini, Alexander A (Contributor), Schwarting, Wilko (Contributor), Bhatia, Sangeeta N (Contributor), Rus, Daniela L (Contributor)
Other Authors: Harvard University- (Contributor), Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Amini, Alexander (Contributor)
Format: Article
Language:English
Published: AAAI/ACM, 2019-03-26T14:39:35Z.
Subjects:
Article
Online Access:Get fulltext

Internet

Get fulltext

Similar Items