Understand
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.
Built on
A data-driven software tool for enabling cooperative information sharing among police departments
Michael Redmond and Alok Baveja. 2002 · 2002
Earlier work this paper cites.
Kernels for multi-task learning. In Advances in Neural Information Processing Systems
Charles A Micchelli and Massimiliano Pontil. 2005 · 2005
Earlier work this paper cites.
To transfer or not to transfer. In NIPS 2005 Workshop on Transfer Learning
Michael T Rosenstein, Zvika Marx, Leslie Pack Kaelbling, and Thomas G Dietterich. 2005 · 2005
Earlier work this paper cites.
Similar
A survey on transfer learning
Sinno Jialin Pan and Qiang Yang. 2010 · 2010
Cited alongside, same era.
Fairness through awareness. In Innovations in Theoretical Computer Science Conference
Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. 2012 · 2012
Cited alongside, same era.
Stability and hypothesis transfer learning. In International Conference on Machine Learning (ICML)
Ilja Kuzborskij and Francesco Orabona. 2013 · 2013
Cited alongside, same era.
Then
Learning fair representations. In International Conference on Machine Learning (ICML)
Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. 2013 · 2013
Later among the works it cites.
Convex learning of multiple tasks and their structure. In International Conference on Machine Learning (ICML)
Carlo Ciliberto, Youssef Mroueh, Tomaso Poggio, and Lorenzo Rosasco. 2015 · 2015
Later among the works it cites.
Equality of opportunity in supervised learning. In Advances in Neural Information Processing Systems (NIPS)
Moritz Hardt, Eric Price, and Nathan Srebro. 2016 · 2016
Later among the works it cites.
Beyond the bibliography
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…