Papadaki, Afroditi;
Martinez, Natalia;
Bertran, Martin;
Sapiro, Guillermo;
Rodrigues, Miguel;
(2022)
Federated Fairness without Access to Demographics.
In:
NeurIPS 2022 Workshop Federated Learning.
: New Orleans, LA, USA.
Preview |
Text
59_federated_fairness_without_acc.pdf - Published Version Download (1MB) | Preview |
Abstract
Existing federated learning approaches address demographic group fairness assuming that clients are aware of the sensitive groups. Such approaches are not applicable in settings where sensitive groups are unidentified or unavailable. In this paper, we address this limitation by focusing on federated learning settings of fairness without demographics. We present a novel objective that allows trade-offs between (worst-case) group fairness and average utility performance through a hyper-parameter and a group size constraint. We show that the proposed objective recovers existing approaches as special cases and then provide an algorithm to efficiently solve the proposed optimization problem. We experimentally showcase the different solutions that can be achieved by our proposed approach and compare it against baselines on various standard datasets.
| Type: | Proceedings paper |
|---|---|
| Title: | Federated Fairness without Access to Demographics |
| Event: | Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022) |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://openreview.net/forum?id=CmmxQQE6U60A |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10192044 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
