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: | en_US |
| Published: |
AAAI/ACM
2019
|
| Online Access: | http://hdl.handle.net/1721.1/121101 https://orcid.org/0000-0002-9673-1267 https://orcid.org/0000-0002-1293-2097 https://orcid.org/0000-0001-5473-3566 |