Back to search

University of Waterloo

REACT: REcourse Analysis with Counterfactuals and Explanation Tables

Abstract

dc:description.abstract

Machine learning models often exhibit not only explicit bias–unequal performance metrics across subgroups–but also implicit bias, where altering a model’s prediction is disproportionately difficult across subgroups. In this work, we investigate two complementary approaches to analyze ways to overturn a model's decision to achieve a desired label: modifying test input features and unlearning a set of training samples. The novelty of our solution lies in combining these two methods with data summarization via informative rule mining that highlights biased subgroups. We demonstrate the value of REACT by allowing users to detect a model’s implicit bias and compare the biases of different model versions. The resulting framework is flexible, supporting the definition of practical constraints on feature-level interventions–for example, by limiting changes to modifiable attributes.

Degree

thesis:*
Grantor dc:publisher
University of Waterloo
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Avksientieva, Anastasiia

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/10012/21759

Chain of custody

source
Harvested from
University of Waterloo
Base URL
dspacemainprd01.lib.uwaterloo.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Avksientieva, Anastasiia. REACT: REcourse Analysis with Counterfactuals and Explanation Tables. University of Waterloo, 2025. https://hdl.handle.net/10012/21759