DeepAI AI Chat
Log In Sign Up

Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data

by   Dylan Slack, et al.
University of California, Irvine
Haverford College

In this paper, we advocate for the study of fairness techniques in low data situations. We propose two algorithms Fairness Warnings and Fair-MAML. The first is a model-agnostic algorithm that provides interpretable boundary conditions for when a fairly trained model may not behave fairly on similar but slightly different tasks within a given domain. The second is a fair meta-learning approach to train models that can be trained through gradient descent with the objective of "learning how to learn fairly". This method encodes more general notions of fairness and accuracy into the model so that it can learn new tasks within a domain both quickly and fairly from only a few training points. We demonstrate experimentally the individual utility of each model using relevant baselines for comparison and provide the first experiment to our knowledge of K-shot fairness, i.e. training a fair model on a new task with only K data points. Then, we illustrate the usefulness of both algorithms as a combined method for training models from a few data points on new tasks while using Fairness Warnings as interpretable boundary conditions under which the newly trained model may not be fair.


page 7

page 11


Fair Meta-Learning: Learning How to Learn Fairly

Data sets for fairness relevant tasks can lack examples or be biased acc...

FaiR-N: Fair and Robust Neural Networks for Structured Data

Fairness in machine learning is crucial when individuals are subject to ...

Fair Meta-Learning For Few-Shot Classification

Artificial intelligence nowadays plays an increasingly prominent role in...

Preserving Fairness in AI under Domain Shift

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

FairShap: A Data Re-weighting Approach for Algorithmic Fairness based on Shapley Values

In this paper, we propose FairShap, a novel and interpretable pre-proces...

Learning Optimal Fair Classification Trees

The increasing use of machine learning in high-stakes domains – where pe...

Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness

We turn the definition of individual fairness on its head—rather than as...