Conference item
When worlds collide: Integrating different counterfactual assumptions in fairness
- Abstract:
-
Machine learning is now being used to make crucial decisions about people's lives. For nearly all of these decisions there is a risk that individuals of a certain race, gender, sexual orientation, or any other subpopulation are unfairly discriminated against. Our recent method has demonstrated how to use techniques from counterfactual inference to make predictions fair across different subpopulations. This method requires that one provides the causal model that generated the data at hand. In ...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Massachusetts Institute of Technology Press Publisher's website
- Host title:
- Advances in Neural Information Processing Systems
- Journal:
- Advances in Neural Information Processing Systems Journal website
- Volume:
- 30
- Pages:
- 6415-6424
- Publication date:
- 2017-01-01
- Acceptance date:
- 2017-12-09
- ISSN:
-
1049-5258
Item Description
- Pubs id:
-
pubs:924093
- UUID:
-
uuid:62fce935-b593-4633-8378-417c645a5130
- Local pid:
- pubs:924093
- Source identifiers:
-
924093
- Deposit date:
- 2019-02-20
Terms of use
- Copyright holder:
- Massachusetts Institute of Technology Press
- Copyright date:
- 2017
- Notes:
- This is a conference paper which was presented at the 31st Conference on Neural Information Processing Systems, 04-09 December 2017, Long Beach, CA, USA. This is the final version of the article which is also available online from Massachusetts Institute of Technology Press at: https://papers.nips.cc/paper/7220-when-worlds-collide-integrating-different-counterfactual-assumptions-in-fairness
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record