Rawlsian fair adaptation of deep learning classifiers
K Shah, P Gupta, A Deshpande… - Proceedings of the 2021 …, 2021 - dl.acm.org
Group-fairness in classification aims for equality of a predictive utility across different
sensitive sub-populations, eg, race or gender. Equality or near-equality constraints in group …
sensitive sub-populations, eg, race or gender. Equality or near-equality constraints in group …
Fnnc: Achieving fairness through neural networks
In classification models fairness can be ensured by solving a constrained optimization
problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and …
problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and …
Blackbox post-processing for multiclass fairness
Applying standard machine learning approaches for classification can produce unequal
results across different demographic groups. When then used in real-world settings, these …
results across different demographic groups. When then used in real-world settings, these …
Conditional learning of fair representations
We propose a novel algorithm for learning fair representations that can simultaneously
mitigate two notions of disparity among different demographic subgroups in the classification …
mitigate two notions of disparity among different demographic subgroups in the classification …
Minimax group fairness: Algorithms and experiments
We consider a recently introduced framework in which fairness is measured by worst-case
outcomes across groups, rather than by the more standard differences between group …
outcomes across groups, rather than by the more standard differences between group …
Designing fairly fair classifiers via economic fairness notions
S Hossain, A Mladenovic, N Shah - Proceedings of The Web …, 2020 - dl.acm.org
The past decade has witnessed a rapid growth of research on fairness in machine learning.
In contrast, fairness has been formally studied for almost a century in microeconomics in the …
In contrast, fairness has been formally studied for almost a century in microeconomics in the …
Group-aware threshold adaptation for fair classification
The fairness in machine learning is getting increasing attention, as its applications in
different fields continue to expand and diversify. To mitigate the discriminated model …
different fields continue to expand and diversify. To mitigate the discriminated model …
Fifa: Making fairness more generalizable in classifiers trained on imbalanced data
Algorithmic fairness plays an important role in machine learning and imposing fairness
constraints during learning is a common approach. However, many datasets are imbalanced …
constraints during learning is a common approach. However, many datasets are imbalanced …
[PDF][PDF] Fnnc: Achieving fairness through neural networks
In classification models, fairness can be ensured by solving a constrained optimization
problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and …
problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and …
Fair Without Leveling Down: A New Intersectional Fairness Definition
In this work, we consider the problem of intersectional group fairness in the classification
setting, where the objective is to learn discrimination-free models in the presence of several …
setting, where the objective is to learn discrimination-free models in the presence of several …