Discriminatory Transfer
Not on the map. Why?
Abstract (arXiv)
We observe standard transfer learning can improve prediction accuracies of target tasks at the cost of lowering their prediction fairness -- a phenomenon we named discriminatory transfer. We examine prediction fairness of a standard hypothesis transfer algorithm and a standard multi-task learning algorithm, and show they both suffer discriminatory transfer on the real-world Communities and Crime data set. The presented case study introduces an interaction between fairness and transfer learning, as an extension of existing fairness studies that focus on single task learning.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jul 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 3; 2023: 1.
4 papers.
- 2022Diagnosing failures of fairness transfer across distribution shift in real-world medical settingscited by 45
- 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularizationcited by 21
- 2022A Survey on Preserving Fairness Guarantees in Changing Environmentscited by 2
- 2023Transferring Fairness using Multi-Task Learning with Limited Demographic Informationcited by 0
- 2023Transferring Fairness using Multi-Task Learning with Limited Demographic Information22 May 2023
- 2022A Survey on Preserving Fairness Guarantees in Changing Environments14 Nov 2022
- 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularization26 Jun 2022
- 2022Diagnosing failures of fairness transfer across distribution shift in real-world medical settings2 Feb 2022