Call for Papers
Abstract Submission Deadline:
September 15 Sep 22, 2022
September 22 Sep 26, 2022
All deadlines are 11:59PM, Anywhere on Earth
Submission portal: https://cmt3.research.microsoft.com/AFCP2022/Submission/Index
The AFCP workshop encourages rigorous discussions among participants from all communities interested in topics of fairness, causality and privacy.
The workshop will include two tracks: a Paper track and an Extended Abstract track.
The Papers track serves to highlight novel contributions that will be presented during the workshop as contributed talks and at the poster session. At the discretion of authors, accepted papers will be published in the workshop proceedings.
The Extended Abstract track welcome early unfinished work that would benefit from feedback from the concentration of experts at the workshop. Accepted submissions will be presented as posters.
Call for Papers
Abstract deadline: September
15 22, Full submission: September 22 26
Paper Submissions should describe new projects aimed at using Causality and/or Privacy to address fairness in machine learning. Submissions should have theoretical or empirical results demonstrating the approach, and specifying how the project fills a gap in the current literature. Authors of accepted papers will be required to upload a 10-min video presentation of their paper. All recorded talks will be made available on the workshop website.
We welcome submissions of novel work in the area of fairness with a special interest on (but not limited to):
- Failure modes of current fairness definitions
- Fairness metrics and mitigation techniques
- Novel, application-specific formalizations of fairness
- Causal definitions of fairness
- Applications of counterfactual fairness
- Methods to encode domain-specific fairness knowledge into causal models
- Studies of practical limitations of causally grounded fairness methods
- Role of counterfactuals in studies of discrimination
- Compatibility of fairness and privacy notions
- Learning fair algorithms from encrypted data
- Privacy-preserving learning of fair algorithms
- Privacy-preserving auditing of algorithmic fairness
- Trade-offs between privacy, fairness and utility
- Policy aspects of data privacy and fairness
4-8 pages not including references and appendix.
The impact statement and checklist are optional and do not count towards the page limit.
Please use the preprint option (with the numbered rows) from the NeurIPS latex template and change the footnote to reflect the name of the workshop.
You can upload supplementary files