Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.22114 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916764020899840 |
|---|---|
| author | Defrance, MaryBeth Bied, Guillaume Buyl, Maarten Lijffijt, Jefrey De Bie, Tijl |
| author_facet | Defrance, MaryBeth Bied, Guillaume Buyl, Maarten Lijffijt, Jefrey De Bie, Tijl |
| contents | Over the past 15 years, hundreds of bias mitigation methods have been proposed in the pursuit of fairness in machine learning (ML). However, algorithmic biases are domain-, task-, and model-specific, leading to a `portability trap': bias mitigation solutions in one context may not be appropriate in another. Thus, a myriad of design choices have to be made when creating a bias mitigation method, such as the formalization of fairness it pursues, and where and how it intervenes in the ML pipeline. This creates challenges in benchmarking and comparing the relative merits of different bias mitigation methods, and limits their uptake by practitioners.
We propose BiMi Sheets as a portable, uniform guide to document the design choices of any bias mitigation method. This enables researchers and practitioners to quickly learn its main characteristics and to compare with their desiderata. Furthermore, the sheets' structure allow for the creation of a structured database of bias mitigation methods. In order to foster the sheets' adoption, we provide a platform for finding and creating BiMi Sheets at bimisheet.com. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22114 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BiMi Sheets: Infosheets for bias mitigation methods Defrance, MaryBeth Bied, Guillaume Buyl, Maarten Lijffijt, Jefrey De Bie, Tijl Machine Learning Over the past 15 years, hundreds of bias mitigation methods have been proposed in the pursuit of fairness in machine learning (ML). However, algorithmic biases are domain-, task-, and model-specific, leading to a `portability trap': bias mitigation solutions in one context may not be appropriate in another. Thus, a myriad of design choices have to be made when creating a bias mitigation method, such as the formalization of fairness it pursues, and where and how it intervenes in the ML pipeline. This creates challenges in benchmarking and comparing the relative merits of different bias mitigation methods, and limits their uptake by practitioners. We propose BiMi Sheets as a portable, uniform guide to document the design choices of any bias mitigation method. This enables researchers and practitioners to quickly learn its main characteristics and to compare with their desiderata. Furthermore, the sheets' structure allow for the creation of a structured database of bias mitigation methods. In order to foster the sheets' adoption, we provide a platform for finding and creating BiMi Sheets at bimisheet.com. |
| title | BiMi Sheets: Infosheets for bias mitigation methods |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.22114 |