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...
Main Authors: | , , , , |
---|---|
Other Authors: | , , , |
Format: | Article |
Language: | English |
Published: |
AAAI/ACM,
2019-03-26T14:39:35Z.
|
Subjects: | |
Online Access: | Get fulltext |