Rényi Fair Inference

By Sina Baharlouei, Maher Nouiehed, Meisam Razaviyayn. 2019

69 citations recorded by the source corpus.

Machine learning algorithms have been increasingly deployed in critical automated decision-making systems that directly affect human lives. When these algorithms are only trained to minimize the training/test error, they could suffer from systematic discrimination against individuals based on their sensitive attributes such as gender or race. Recently, there has been a surge in machine learning society to develop algorithms for fair machine learning. In particular, many adversarial learning procedures have been proposed to impose fairness. Unfortunately, these algorithms either can only impose fairness up to first-order dependence between the variables, or they lack computational convergence guarantees. In this paper, we use Renyi correlation as a measure of fairness of machine learning models and develop a general training framework to impose fairness. In particular, we propose a min-max formulation which balances the accuracy and fairness when solved to optimality. For the case of discrete sensitive attributes, we suggest an iterative algorithm with theoretical convergence guarantee for solving the proposed min-max problem. Our algorithm and analysis are then specialized to fair classification and the fair clustering problem under disparate impact doctrine. Finally, the performance of the proposed Renyi fair inference framework is evaluated on Adult and Bank datasets.

Subfields: Artificial Intelligence, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tian Li
2. Virginia Smith
3. Maziar Sanjabi
4. Ahmad Beirami
5. Vikram V. Ramaswamy
6. Sunnie S. Y. Kim
7. Olga Russakovsky
8. Jakub Konecný

In Safety Research

1. Vikram V. Ramaswamy
2. Sunnie S. Y. Kim
3. Virginia Smith
4. Tian Li
5. Maziar Sanjabi
6. Olga Russakovsky

Citations in the corpus

• Fair Resource Allocation in Federated Learning (2019, background): “Another set of works optimize an objective subject to some fairness constraints during training time (Agarwal et al., 2018; Cotter et al., 2019; Hashimoto et al., 2018; Woodworth et al., 2017; Baharlouei et al., 2020; Zafar et al., 2017a;b; Dwork et al., 2012).”
• Fair Attribute Classification through Latent Space De-biasing (2020, background): “Other work improve fairness by introducing constraints [29] or regularization terms [3] during training.”
• Tilted Empirical Risk Minimization (2020, background): “Constraints could also be imposed to promote fairness (Baharlouei et al., 2020; Donini et al., 2018; Hardt et al., 2016; Rezaei et al., 2020; Zafar et al., 2017).”