Fairness-aware Federated Minimax Optimization with Convergence Guarantee
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916442215022592 |
|---|---|
| author | Dunda, Gerry Windiarto Mohamad Song, Shenghui |
| author_facet | Dunda, Gerry Windiarto Mohamad Song, Shenghui |
| contents | Federated learning (FL) has garnered considerable attention due to its privacy-preserving feature. Nonetheless, the lack of freedom in managing user data can lead to group fairness issues, where models are biased towards sensitive factors such as race or gender. To tackle this issue, this paper proposes a novel algorithm, fair federated averaging with augmented Lagrangian method (FFALM), designed explicitly to address group fairness issues in FL. Specifically, we impose a fairness constraint on the training objective and solve the minimax reformulation of the constrained optimization problem. Then, we derive the theoretical upper bound for the convergence rate of FFALM. The effectiveness of FFALM in improving fairness is shown empirically on CelebA and UTKFace datasets in the presence of severe statistical heterogeneity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_04417 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Fairness-aware Federated Minimax Optimization with Convergence Guarantee Dunda, Gerry Windiarto Mohamad Song, Shenghui Machine Learning Computers and Society Federated learning (FL) has garnered considerable attention due to its privacy-preserving feature. Nonetheless, the lack of freedom in managing user data can lead to group fairness issues, where models are biased towards sensitive factors such as race or gender. To tackle this issue, this paper proposes a novel algorithm, fair federated averaging with augmented Lagrangian method (FFALM), designed explicitly to address group fairness issues in FL. Specifically, we impose a fairness constraint on the training objective and solve the minimax reformulation of the constrained optimization problem. Then, we derive the theoretical upper bound for the convergence rate of FFALM. The effectiveness of FFALM in improving fairness is shown empirically on CelebA and UTKFace datasets in the presence of severe statistical heterogeneity. |
| title | Fairness-aware Federated Minimax Optimization with Convergence Guarantee |
| topic | Machine Learning Computers and Society |
| url | https://arxiv.org/abs/2307.04417 |