Leave-one-out Unfairness

07/21/2021
by   Emily Black, et al.
0

We introduce leave-one-out unfairness, which characterizes how likely a model's prediction for an individual will change due to the inclusion or removal of a single other person in the model's training data. Leave-one-out unfairness appeals to the idea that fair decisions are not arbitrary: they should not be based on the chance event of any one person's inclusion in the training data. Leave-one-out unfairness is closely related to algorithmic stability, but it focuses on the consistency of an individual point's prediction outcome over unit changes to the training data, rather than the error of the model in aggregate. Beyond formalizing leave-one-out unfairness, we characterize the extent to which deep models behave leave-one-out unfairly on real data, including in cases where the generalization error is small. Further, we demonstrate that adversarial training and randomized smoothing techniques have opposite effects on leave-one-out fairness, which sheds light on the relationships between robustness, memorization, individual fairness, and leave-one-out fairness in deep models. Finally, we discuss salient practical applications that may be negatively affected by leave-one-out unfairness.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

02/18/2020

Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness

We turn the definition of individual fairness on its head—rather than as...
11/07/2020

On the Privacy Risks of Algorithmic Fairness

Algorithmic fairness and privacy are essential elements of trustworthy m...
01/08/2021

A Tale of Fairness Revisited: Beyond Adversarial Learning for Deep Neural Network Fairness

Motivated by the need for fair algorithmic decision making in the age of...
10/06/2021

Consistent Counterfactuals for Deep Models

Counterfactual examples are one of the most commonly-cited methods for e...
12/21/2020

The Importance of Modeling Data Missingness in Algorithmic Fairness: A Causal Perspective

Training datasets for machine learning often have some form of missingne...
09/28/2020

Towards a Measure of Individual Fairness for Deep Learning

Deep learning has produced big advances in artificial intelligence, but ...
05/07/2021

Human-Aided Saliency Maps Improve Generalization of Deep Learning

Deep learning has driven remarkable accuracy increases in many computer ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.