Year: 2022
Type: article
Abstract: 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. The resulting problem is that of censoring, i.e., finding a representation that is least informative about the sensitive attributes given a utility constraint. For appropriately chosen adversarial loss functions, our censoring 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 evaluate the performance of our proposed framework on both synthetic and publicly available datasets. For these datasets, we use two tradeoff measures: censoring vs. representation fidelity and fairness vs. utility for downstream tasks, to amply demonstrate that multiple sensitive features can be effectively censored even as the resulting fair representations ensure accuracy for multiple downstream tasks.
Institutions: Google (United States), Arizona State University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
Awards: CIF: Small: Collaborative Research: Generative Adversarial Privacy: A Data-driven Approach to Guaranteeing Privacy and Utility, Unifying Information- and Optimization-Theoretic Approaches for Modeling and Training Generative Adversarial Networks, RAPID: SaTC: FACT: Federated Analytics based Contact Tracing for COVID-19, CAREER: Privacy-Guaranteed Distributed Interactions in Critical Infrastructure Networks, CIF: Small: Alpha Loss: A New Framework for Understanding and Trading Off Computation, Accuracy, and Robustness in Machine Learning, CIF: Medium: Collaborative Research: Information-theoretic Guarantees on Privacy in the Age of Learning
OpenAlex ID: W3159744177