Mitigating Unwanted Biases with Adversarial Learning

by   Brian Hu Zhang, et al.

Machine learning is a tool for building models that accurately represent input training data. When undesired biases concerning demographic groups are in the training data, well-trained models will reflect those biases. We present a framework for mitigating such biases by including a variable for the group of interest and simultaneously learning a predictor and an adversary. The input to the network X, here text or census data, produces a prediction Y, such as an analogy completion or income bracket, while the adversary tries to model a protected variable Z, here gender or zip code. The objective is to maximize the predictor's ability to predict Y while minimizing the adversary's ability to predict Z. Applied to analogy completion, this method results in accurate predictions that exhibit less evidence of stereotyping Z. When applied to a classification task using the UCI Adult (Census) Dataset, it results in a predictive model that does not lose much accuracy while achieving very close to equality of odds (Hardt, et al., 2016). The method is flexible and applicable to multiple definitions of fairness as well as a wide range of gradient-based learning models, including both regression and classification tasks.


page 1

page 2

page 3

page 4


A Machine Learning Model for Predicting, Diagnosing, and Mitigating Health Disparities in Hospital Readmission

The management of hyperglycemia in hospitalized patients has a significa...

Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

In consequential decision-making applications, mitigating unwanted biase...

Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness

Data-driven predictive solutions predominant in commercial applications ...

A Systematic Study of Bias Amplification

Recent research suggests that predictions made by machine-learning model...

Ethical Adversaries: Towards Mitigating Unfairness with Adversarial Machine Learning

Machine learning is being integrated into a growing number of critical s...

Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings

Neural networks achieve the state-of-the-art in image classification tas...

Censoring Representations with an Adversary

In practice, there are often explicit constraints on what representation...

Please sign up or login with your details

Forgot password? Click here to reset