Graduation Semester and Year
2022
Language
English
Document Type
Thesis
Degree Name
Master of Science in Computer Science
Department
Computer Science and Engineering
First Advisor
Yu Lei
Abstract
Machine Learning (ML) models could exhibit biased behavior, or algorithmic discrimination, resulting in unfair or discriminatory outcomes. The bias in the ML model could emanate from various factors such as the training dataset, the choice of the ML algorithm, or the hyperparameters used to train the ML model. In addition to evaluating the model’s correctness, it is essential to test ML models for fair and unbiased behavior. In this thesis, we present a combinatorial testing-based approach to perform fairness testing of ML models. Our approach is model agnostic and evaluates fairness violations of a pre-trained ML model in a two-step process. In the first step, we create an input parameter model from the training data set and then use the model to generate a t-way test set. In the second step, for each test, we modify the value of one or more protected attributes to see if we could find fairness violations. We performed an experimental evaluation of the proposed approach using ML models trained with tabular datasets. The results suggest that the proposed approach can successfully identify fairness violations in pre-trained ML models. This thesis is presented in an article-based format and includes a research paper. This paper reports our work on applying combinatorial testing to identify fairness violations in Machine Learning (ML) models. This paper has been accepted at a peer-reviewed venue (In press).
Keywords
Fairness testing, Algorithmic discrimination, Bias detection, Testing model bias, Testing ML model, Combinatorial testing
Disciplines
Computer Sciences | Physical Sciences and Mathematics
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Patel, Ankita Ramjibhai, "A COMBINATORIAL APPROACH TO FAIRNESS TESTING OF MACHINE LEARNING MODELS" (2022). Computer Science and Engineering Theses. 429.
https://mavmatrix.uta.edu/cse_theses/429
Comments
Degree granted by The University of Texas at Arlington