One-Network Adversarial Fairness

Adel, T. , Valera, I., Ghahramani, Z. and Weller, A. (2019) One-Network Adversarial Fairness. In: 33rd AAAI Conference on Artificial Intelligence (AAAI-19), Honolulu, HI, USA, 27 Jan - 1 Feb 2019, pp. 2412-2420. (doi:10.1609/aaai.v33i01.33012412)

Full text not currently available from Enlighten.


There is currently a great expansion of the impact of machine learning algorithms on our lives, prompting the need for objectives other than pure performance, including fairness. Fairness here means that the outcome of an automated decisionmaking system should not discriminate between subgroups characterized by sensitive attributes such as gender or race. Given any existing differentiable classifier, we make only slight adjustments to the architecture including adding a new hidden layer, in order to enable the concurrent adversarial optimization for fairness and accuracy. Our framework provides one way to quantify the tradeoff between fairness and accuracy, while also leading to strong empirical performance.

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Hesham, Dr Tameem Adel
Authors: Adel, T., Valera, I., Ghahramani, Z., and Weller, A.
College/School:College of Science and Engineering > School of Computing Science
Journal Name:Proceedings of the AAAI Conference on Artificial Intelligence

University Staff: Request a correction | Enlighten Editors: Update this record