DeepAI AI Chat
Log In Sign Up

Multiaccurate Proxies for Downstream Fairness

by   Emily Diana, et al.

We study the problem of training a model that must obey demographic fairness conditions when the sensitive features are not available at training time – in other words, how can we train a model to be fair by race when we don't have data about race? We adopt a fairness pipeline perspective, in which an "upstream" learner that does have access to the sensitive features will learn a proxy model for these features from the other attributes. The goal of the proxy is to allow a general "downstream" learner – with minimal assumptions on their prediction task – to be able to use the proxy to train a model that is fair with respect to the true sensitive features. We show that obeying multiaccuracy constraints with respect to the downstream model class suffices for this purpose, and provide sample- and oracle efficient-algorithms and generalization bounds for learning such proxies. In general, multiaccuracy can be much easier to satisfy than classification accuracy, and can be satisfied even when the sensitive features are hard to predict.


page 1

page 2

page 3

page 4


Estimating and Controlling for Fairness via Sensitive Attribute Predictors

Although machine learning classifiers have been increasingly used in hig...

Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access

Fair machine learning methods seek to train models that balance model pe...

Fair Decision-Making for Food Inspections

We revisit the application of predictive models by the Chicago Departmen...

Model Debiasing via Gradient-based Explanation on Representation

Machine learning systems produce biased results towards certain demograp...

Fair Visual Recognition via Intervention with Proxy Features

Deep learning models often learn to make predictions that rely on sensit...

Blind Justice: Fairness with Encrypted Sensitive Attributes

Recent work has explored how to train machine learning models which do n...

Crowdsourcing with Fairness, Diversity and Budget Constraints

Recent studies have shown that the labels collected from crowdworkers ca...