Controlling bias in training datasets is vital for ensuring equal treatment, or parity, between different groups in downstream applications. A naive solution is to transform the data so that it is statistically independent of group membership, but this may throw away too much information when a reasonable compromise between fairness and accuracy is desired. Another common approach is to limit the ability of a particular adversary who seeks to maximize parity. Unfortunately, representations produced by adversarial approaches may still retain biases as their efficacy is tied to the complexity of the adversary used during training. To this end, we theoretically establish that by limiting the mutual information between representations and prote...
Fairness in machine learning is getting rising attention as it is directly related to real-world app...
There is currently a great expansion of the impact of machine learning algorithms on our lives, prom...
The concerns regarding ramifications of societal bias targeted at a particular identity group (for e...
Developing learning methods which do not discriminate subgroups in the population is the central goa...
Developing learning methods which do not discriminate subgroups in the population is a central goal ...
We present a data-driven framework for learning \textit{censored and fair universal representations}...
Computer vision algorithms, e.g. for face recognition, favour groups of individuals that are better ...
Bias in training datasets must be managed for various groups in classification tasks to ensure parit...
In recent years, a growing body of work has emerged on how to learn machine learning models under fa...
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce seve...
Fair representation learning provides an effective way of enforcing fairness constraints without com...
We propose a novel algorithm for learning fair representations that can simultaneously mitigate two ...
A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidabl...
In recent years, a great deal of fairness notions has been proposed. Yet, most of them take a reduct...
As they have a vital effect on social decision-making, AI algorithms should be not only accurate but...
Fairness in machine learning is getting rising attention as it is directly related to real-world app...
There is currently a great expansion of the impact of machine learning algorithms on our lives, prom...
The concerns regarding ramifications of societal bias targeted at a particular identity group (for e...
Developing learning methods which do not discriminate subgroups in the population is the central goa...
Developing learning methods which do not discriminate subgroups in the population is a central goal ...
We present a data-driven framework for learning \textit{censored and fair universal representations}...
Computer vision algorithms, e.g. for face recognition, favour groups of individuals that are better ...
Bias in training datasets must be managed for various groups in classification tasks to ensure parit...
In recent years, a growing body of work has emerged on how to learn machine learning models under fa...
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce seve...
Fair representation learning provides an effective way of enforcing fairness constraints without com...
We propose a novel algorithm for learning fair representations that can simultaneously mitigate two ...
A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidabl...
In recent years, a great deal of fairness notions has been proposed. Yet, most of them take a reduct...
As they have a vital effect on social decision-making, AI algorithms should be not only accurate but...
Fairness in machine learning is getting rising attention as it is directly related to real-world app...
There is currently a great expansion of the impact of machine learning algorithms on our lives, prom...
The concerns regarding ramifications of societal bias targeted at a particular identity group (for e...