BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912052515176448 |
|---|---|
| author | Xue, Yuyang Yan, Junyu Dutt, Raman Haider, Fasih Liu, Jingshuai McDonagh, Steven Tsaftaris, Sotirios A. |
| author_facet | Xue, Yuyang Yan, Junyu Dutt, Raman Haider, Fasih Liu, Jingshuai McDonagh, Steven Tsaftaris, Sotirios A. |
| contents | Developing models with robust group fairness properties is paramount, particularly in ethically sensitive domains such as medical diagnosis. Recent approaches to achieving fairness in machine learning require a substantial amount of training data and depend on model retraining, which may not be practical in real-world scenarios. To mitigate these challenges, we propose Bias-based Weight Masking Fine-Tuning (BMFT), a novel post-processing method that enhances the fairness of a trained model in significantly fewer epochs without requiring access to the original training data. BMFT produces a mask over model parameters, which efficiently identifies the weights contributing the most towards biased predictions. Furthermore, we propose a two-step debiasing strategy, wherein the feature extractor undergoes initial fine-tuning on the identified bias-influenced weights, succeeded by a fine-tuning phase on a reinitialised classification layer to uphold discriminative performance. Extensive experiments across four dermatological datasets and two sensitive attributes demonstrate that BMFT outperforms existing state-of-the-art (SOTA) techniques in both diagnostic accuracy and fairness metrics. Our findings underscore the efficacy and robustness of BMFT in advancing fairness across various out-of-distribution (OOD) settings. Our code is available at: https://github.com/vios-s/BMFT |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06890 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning Xue, Yuyang Yan, Junyu Dutt, Raman Haider, Fasih Liu, Jingshuai McDonagh, Steven Tsaftaris, Sotirios A. Machine Learning Artificial Intelligence Developing models with robust group fairness properties is paramount, particularly in ethically sensitive domains such as medical diagnosis. Recent approaches to achieving fairness in machine learning require a substantial amount of training data and depend on model retraining, which may not be practical in real-world scenarios. To mitigate these challenges, we propose Bias-based Weight Masking Fine-Tuning (BMFT), a novel post-processing method that enhances the fairness of a trained model in significantly fewer epochs without requiring access to the original training data. BMFT produces a mask over model parameters, which efficiently identifies the weights contributing the most towards biased predictions. Furthermore, we propose a two-step debiasing strategy, wherein the feature extractor undergoes initial fine-tuning on the identified bias-influenced weights, succeeded by a fine-tuning phase on a reinitialised classification layer to uphold discriminative performance. Extensive experiments across four dermatological datasets and two sensitive attributes demonstrate that BMFT outperforms existing state-of-the-art (SOTA) techniques in both diagnostic accuracy and fairness metrics. Our findings underscore the efficacy and robustness of BMFT in advancing fairness across various out-of-distribution (OOD) settings. Our code is available at: https://github.com/vios-s/BMFT |
| title | BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.06890 |