Timezone: »

Learning Adversarially Fair and Transferable Representations
David Madras · Elliot Creager · Toniann Pitassi · Richard Zemel

Fri Jul 13 09:15 AM -- 12:00 PM (PDT) @ Hall B #44

In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair prediction. Furthermore, we present the first in-depth experimental demonstration of fair transfer learning and demonstrate empirically that our learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.

Author Information

David Madras (University of Toronto)
Elliot Creager (University of Toronto)
Toniann Pitassi (University of Toronto)
Richard Zemel (Vector Institute)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors