Timezone: »

 
Fair Universal Representations using Adversarial Models
Monica Welfert · Peter Kairouz · Jiachun Liao · Chong Huang · Lalitha Sankar

@
in New Frontiers in Adversarial Machine Learning »

We present a data-driven framework for learning fair universal representations (FUR) that guarantee statistical fairness for any learning task that may not be known a priori. Our framework leverages recent advances in adversarial learning to allow a data holder to learn representations in which a set of sensitive attributes are decoupled from the rest of the dataset. We formulate this as a constrained minimax game between an encoder and an adversary where the constraint ensures a measure of usefulness (utility) of the representation. For appropriately chosen adversarial loss functions, our framework precisely clarifies the optimal adversarial strategy against strong information-theoretic adversaries; it also achieves the fairness measure of demographic parity for the resulting constrained representations. We highlight our results for the UCI Adult and UTKFace datasets.

Author Information

Monica Welfert (Arizona State University)
Peter Kairouz (Google)
Jiachun Liao (ASU)
Chong Huang (Arizona State University)
Lalitha Sankar (Arizona State University)

More from the Same Authors