Improved Adversarial Learning for Fair Classification

by   L. Elisa Celis, et al.

Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machine learning research. One important paradigm towards this has been providing algorithms for adversarially learning fair classifiers (Zhang et al., 2018; Madras et al., 2018). We formulate the adversarial learning problem as a multi-objective optimization problem and find the fair model using gradient descent-ascent algorithm with a modified gradient update step, inspired by the approach of Zhang et al., 2018. We provide theoretical insight and guarantees that formalize the heuristic arguments presented previously towards taking such an approach. We test our approach empirically on the Adult dataset and synthetic datasets and compare against state of the art algorithms (Celis et al., 2018; Zhang et al., 2018; Zafar et al., 2017). The results show that our models and algorithms have comparable or better accuracy than other algorithms while performing better in terms of fairness, as measured using statistical rate or false discovery rate.


page 1

page 2

page 3

page 4


Fair Adversarial Gradient Tree Boosting

Fair classification has become an important topic in machine learning re...

Data Preprocessing to Mitigate Bias with Boosted Fair Mollifiers

In a recent paper, Celis et al. (2020) introduced a new approach to fair...

Adversarial Learning and Explainability in Structured Datasets

We theoretically and empirically explore the explainability benefits of ...

Stable and Fair Classification

Fair classification has been a topic of intense study in machine learnin...

Transfer learning to enhance amenorrhea status prediction in cancer and fertility data with missing values

Collecting sufficient labelled training data for health and medical prob...

Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms

The question why deep learning algorithms generalize so well has attract...

Facies classification from well logs using an inception convolutional network

The idea to use automated algorithms to determine geological facies from...

Please sign up or login with your details

Forgot password? Click here to reset