Back to search

University of Washington

Deep Reinforcement Learning for Data-Agnostic Post-Training Debiasing of Black-Box Machine Learning Models

Abstract

dc:description.abstract

As reliance on Machine Learning systems in real-world decision-making processes grows, ensuring these systems are free of bias against sensitive demographic groups is of increasing importance. Existing techniques for automatically debiasing ML models generally require access to either the models’ internal architectures, the models’ training datasets, or both. In this paper we outline the reasons why such requirements are disadvantageous, and present an alternative novel debiasing system that is both data- and model-agnostic. We implement this system as a Reinforcement Learning Agent and employ it to debias four target ML model architectures over three datasets. Our results show performance comparable to data- and/or model-gnostic state-of-the-art debiasers.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Pinkava, Thomas
Advisor dc:contributor.advisor
  • Mashhadi, Afra

Subjects

dc:subject × 7

Rights

dc:rights
Statement dc:rights
  • CC BY-NC-SA
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1773/51650

Chain of custody

source
Harvested from
University of Washington
Base URL
digital.lib.washington.edu/server/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Pinkava, Thomas. Deep Reinforcement Learning for Data-Agnostic Post-Training Debiasing of Black-Box Machine Learning Models. 2024. https://hdl.handle.net/1773/51650