Back to search

Michigan State University

Learning fair representations without demographics

Abstract

dc:description

Due to hard accessibility, real-world adoption of fair representation learning algorithms lacks the prior knowledge of the sensitive attributes that we wish to be fair with. To address the challenge in fairness without explicit demographics, our solution is based on the idea of maximally randomizing the representation while being as informative as possible about the target task. We operationalize this goal through the concept of maximizing the entropy of the learned representation. For this purpose, we propose two new avenues for entropy maximization in the absence of demographic information: intra-class and inter-class entropy maximization. For 1) intra-class entropy maximization, it maximizes the entropy of the non-target class predictions (excluding the probability of the ground truth class label for classification problems), thus encouraging the model to discard spurious correlations between the different target classes, and for 2) inter-class entropy maximization, it maximizes the entropy of the representation conditioned on the target label, thus encouraging randomization of the samples within each target class label and minimizing the leakage of potential demographic information in the representation. Quantitative and qualitative results of our Maximum Entropy method (MaxEnt) on COMPAS and UCI Adult datasets show that 1) our method can outperform the State-of-the-art (SOTA) Adversarially Reweighted Learning (ARL) method and will enhance the difficulty of extracting sensitive demographic information in representation without prior demographic knowledge 2) our method reaches a good trade-off between utility and fairness.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Wang, Xiaoxue
Contributors dc:contributor
  • Boddeti, Vishnu
  • Ross, Arun
  • Tang, Jiliang

Subjects

dc:subject × 2

Rights

dc:rights
Statement dc:rights
  • In Copyright
Language dc:language
English

Identifiers

dc:identifier.*
Identifier
etd:50366
isbn:9798426831827
oclc:on1345375213
oclc:1345375213
umi:29165050
local:Wang_grad.msu_0128N_18992

Chain of custody

source
Harvested from
Michigan State University
Base URL
d.lib.msu.edu/oai
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Wang, Xiaoxue. Learning fair representations without demographics. 2022. https://doi.org/doi:10.25335/khvc-ym69