| Title: | Fostering fairness in image classification through awareness of sensitive data |
|---|
| Authors: | ID Colakovic, Ivona (Author)
ID Karakatič, Sašo (Author) |
|---|
| Files: |  1-s2.0-S1568494625004016-main.pdf (2,01 MB)
MD5: 131792810C6ABE1A402EC5820F6B701B
 https://www.sciencedirect.com/science/article/pii/S1568494625004016?via%3Dihub#sec3
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
|
|---|
| Abstract: | Machine learning (ML) has demonstrated remarkable ability to uncover hidden patterns in data. However, the presence of biases and discrimination originating from the data itself and, consequently, emerging in the ML outcomes, remains a pressing concern. With the exponential growth of unstructured data, such as images, fairness has become increasingly critical, as neural network (NN) models may inadvertently learn and perpetuate societal and historical biases. To address this challenge, we propose a fairness-aware loss function that iteratively prioritizes the worst-performing sensitive group during NN training. This approach aims to balance treatment quality across sensitive groups, achieving fairer image classification outcomes while incurring only a slight compromise in overall performance. Our method, evaluated on the FairFace dataset, demonstrates significant improvements in fairness metrics while maintaining comparable overall quality. These trade-offs highlight that the minor decrease in overall quality is justified by the improvement in fairness of the models. |
|---|
| Keywords: | fairness, search-basimage classification, machine learning, supervised learnign, neural networks |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 05.11.2024 |
|---|
| Article acceptance date: | 22.03.2025 |
|---|
| Publication date: | 04.04.2025 |
|---|
| Publisher: | Elsevier |
|---|
| Year of publishing: | 2025 |
|---|
| Number of pages: | 10 str. |
|---|
| Numbering: | Vol. 136, [article] no.] 113090 |
|---|
| PID: | 20.500.12556/DKUM-92602  |
|---|
| UDC: | 004.8 |
|---|
| ISSN on article: | 1872-9681 |
|---|
| COBISS.SI-ID: | 232495363 |
|---|
| DOI: | 10.1016/j.asoc.2025.113090 |
|---|
| Copyright: | © 2025 The Authors |
|---|
| Publication date in DKUM: | 23.04.2025 |
|---|
| Views: | 340 |
|---|
| Downloads: | 11 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
