Flexibly Fair Representation Learning by Disentanglement

06/06/2019
by   Elliot Creager, et al.
4

We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also flexibly fair, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder---which does not require the sensitive attributes for inference---enables the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/04/2023

On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representations

Mitigating the discrimination of machine learning models has gained incr...
research
06/15/2020

Learning Smooth and Fair Representations

Organizations that own data face increasing legal liability for its disc...
research
02/17/2018

Learning Adversarially Fair and Transferable Representations

In this work, we advocate for representation learning as the key to miti...
research
11/15/2022

MMD-B-Fair: Learning Fair Representations with Statistical Testing

We introduce a method, MMD-B-Fair, to learn fair representations of data...
research
02/22/2018

Path-Specific Counterfactual Fairness

We consider the problem of learning fair decision systems in complex sce...
research
12/17/2018

BriarPatches: Pixel-Space Interventions for Inducing Demographic Parity

We introduce the BriarPatch, a pixel-space intervention that obscures se...
research
06/23/2021

Fairness for Image Generation with Uncertain Sensitive Attributes

This work tackles the issue of fairness in the context of generative pro...

Please sign up or login with your details

Forgot password? Click here to reset