Awareness in practice: tensions in access to sensitive attribute data for antidiscrimination
Organizations cannot address demographic disparities that they cannot see. Recent
research on machine learning and fairness has emphasized that awareness of sensitive …
research on machine learning and fairness has emphasized that awareness of sensitive …
What we can't measure, we can't understand: Challenges to demographic data procurement in the pursuit of fairness
As calls for fair and unbiased algorithmic systems increase, so too does the number of
individuals working on algorithmic fairness in industry. However, these practitioners often do …
individuals working on algorithmic fairness in industry. However, these practitioners often do …
Fairer machine learning in the real world: Mitigating discrimination without collecting sensitive data
Decisions based on algorithmic, machine learning models can be unfair, reproducing biases
in historical data used to train them. While computational techniques are emerging to …
in historical data used to train them. While computational techniques are emerging to …
The Privacy-Bias Tradeoff: Data Minimization and Racial Disparity Assessments in US Government
An emerging concern in algorithmic fairness is the tension with privacy interests. Data
minimization can restrict access to protected attributes, such as race and ethnicity, for bias …
minimization can restrict access to protected attributes, such as race and ethnicity, for bias …
Can querying for bias leak protected attributes? achieving privacy with smooth sensitivity
Existing regulations often prohibit model developers from accessing protected attributes
(gender, race, etc.) during training. This leads to scenarios where fairness assessments …
(gender, race, etc.) during training. This leads to scenarios where fairness assessments …
How redundant are redundant encodings? blindness in the wild and racial disparity when race is unobserved
We address two emerging concerns in algorithmic fairness:(i) redundant encodings of race–
the notion that machine learning models encode race with probability nearing one as the …
the notion that machine learning models encode race with probability nearing one as the …
Themis-ml: A fairness-aware machine learning interface for end-to-end discrimination discovery and mitigation
N Bantilan - Journal of Technology in Human Services, 2018 - Taylor & Francis
As more industries integrate machine learning into socially sensitive decision processes like
hiring, loan-approval, and parole-granting, we are at risk of perpetuating historical and …
hiring, loan-approval, and parole-granting, we are at risk of perpetuating historical and …
Data augmentation for discrimination prevention and bias disambiguation
Machine learning models are prone to biased decisions due to biases in the datasets they
are trained on. In this paper, we introduce a novel data augmentation technique to create a …
are trained on. In this paper, we introduce a novel data augmentation technique to create a …
Fairness under unawareness: Assessing disparity when protected class is unobserved
Assessing the fairness of a decision making system with respect to a protected class, such
as gender or race, is challenging when class membership labels are unavailable …
as gender or race, is challenging when class membership labels are unavailable …
Toward accountable discrimination-aware data mining: the Importance of keeping the human in the loop—and under the looking glass
B Berendt, S Preibusch - Big data, 2017 - liebertpub.com
Abstract “Big Data” and data-mined inferences are affecting more and more of our lives, and
concerns about their possible discriminatory effects are growing. Methods for discrimination …
concerns about their possible discriminatory effects are growing. Methods for discrimination …