Learning Fairer Representations with FairVIC
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912661208301568 |
|---|---|
| author | Barker, Charmaine Bethell, Daniel Kazakov, Dimitar |
| author_facet | Barker, Charmaine Bethell, Daniel Kazakov, Dimitar |
| contents | Mitigating bias in automated decision-making systems, particularly in deep learning models, is a critical challenge due to nuanced definitions of fairness, dataset-specific biases, and the inherent trade-off between fairness and accuracy. To address these issues, we introduce FairVIC, an innovative approach that enhances fairness in neural networks by integrating variance, invariance, and covariance terms into the loss function during training. Unlike methods that rely on predefined fairness criteria, FairVIC abstracts fairness concepts to minimise dependency on protected characteristics. We evaluate FairVIC against comparable bias mitigation techniques on benchmark datasets, considering both group and individual fairness, and conduct an ablation study on the accuracy-fairness trade-off. FairVIC demonstrates significant improvements ($\approx70\%$) in fairness across all tested metrics without compromising accuracy, thus offering a robust, generalisable solution for fair deep learning across diverse tasks and datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18134 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Fairer Representations with FairVIC Barker, Charmaine Bethell, Daniel Kazakov, Dimitar Machine Learning Artificial Intelligence Computers and Society Mitigating bias in automated decision-making systems, particularly in deep learning models, is a critical challenge due to nuanced definitions of fairness, dataset-specific biases, and the inherent trade-off between fairness and accuracy. To address these issues, we introduce FairVIC, an innovative approach that enhances fairness in neural networks by integrating variance, invariance, and covariance terms into the loss function during training. Unlike methods that rely on predefined fairness criteria, FairVIC abstracts fairness concepts to minimise dependency on protected characteristics. We evaluate FairVIC against comparable bias mitigation techniques on benchmark datasets, considering both group and individual fairness, and conduct an ablation study on the accuracy-fairness trade-off. FairVIC demonstrates significant improvements ($\approx70\%$) in fairness across all tested metrics without compromising accuracy, thus offering a robust, generalisable solution for fair deep learning across diverse tasks and datasets. |
| title | Learning Fairer Representations with FairVIC |
| topic | Machine Learning Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2404.18134 |