Transfer of Machine Learning Fairness across Domains

06/24/2019
by   Candice Schumann, et al.
4

If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem domain. However, this is often not how models are trained and used in practice. For example, labels and demographics (sensitive attributes) are often hard to observe, resulting in auxiliary or synthetic data to be used for training, and proxies of the sensitive attribute to be used for evaluation of fairness. A model trained for one setting may be picked up and used in many others, particularly as is common with pre-training and cloud APIs. Despite the pervasiveness of these complexities, remarkably little work in the fairness literature has theoretically examined these issues. We frame all of these settings as domain adaptation problems: how can we use what we have learned in a source domain to debias in a new target domain, without directly debiasing on the target domain as if it is a completely new problem? We offer new theoretical guarantees of improving fairness across domains, and offer a modeling approach to transfer to data-sparse target domains. We give empirical results validating the theory and showing that these modeling approaches can improve fairness metrics with less data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/08/2022

Joint Adversarial Learning for Cross-domain Fair Classification

Modern machine learning (ML) models are becoming increasingly popular an...
research
12/19/2022

Source-Free Domain Adaptation for Question Answering with Masked Self-training

Most previous unsupervised domain adaptation (UDA) methods for question ...
research
10/20/2020

Teacher-Student Consistency For Multi-Source Domain Adaptation

In Multi-Source Domain Adaptation (MSDA), models are trained on samples ...
research
09/02/2022

Domain Adaptation from Scratch

Natural language processing (NLP) algorithms are rapidly improving but o...
research
02/27/2023

Domain Adaptive Decision Trees: Implications for Accuracy and Fairness

In uses of pre-trained machine learning models, it is a known issue that...
research
03/29/2021

Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation

Domain adaptation is to transfer the shared knowledge learned from the s...
research
01/29/2023

Preserving Fairness in AI under Domain Shift

Existing algorithms for ensuring fairness in AI use a single-shot traini...

Please sign up or login with your details

Forgot password? Click here to reset