Timezone: »

 
Spotlight
Fairness for Image Generation with Uncertain Sensitive Attributes
Ajil Jalal · Sushrut Karmalkar · Jessica Hoffmann · Alexandros Dimakis · Eric Price

Thu Jul 22 05:30 AM -- 05:35 AM (PDT) @
in Fairness »

This work tackles the issue of fairness in the context of generative procedures, such as image super-resolution, which entail different definitions from the standard classification setting. Moreover, while traditional group fairness definitions are typically defined with respect to specified protected groups -- camouflaging the fact that these groupings are artificial and carry historical and political motivations -- we emphasize that there are no ground truth identities. For instance, should South and East Asians be viewed as a single group or separate groups? Should we consider one race as a whole or further split by gender? Choosing which groups are valid and who belongs in them is an impossible dilemma and being fair'' with respect to Asians may require beingunfair'' with respect to South Asians. This motivates the introduction of definitions that allow algorithms to be \emph{oblivious} to the relevant groupings.

We define several intuitive notions of group fairness and study their incompatibilities and trade-offs. We show that the natural extension of demographic parity is strongly dependent on the grouping, and \emph{impossible} to achieve obliviously. On the other hand, the conceptually new definition we introduce, Conditional Proportional Representation, can be achieved obliviously through Posterior Sampling. Our experiments validate our theoretical results and achieve fair image reconstruction using state-of-the-art generative models.

Keywords: Fairness, Accountability, and Transparency · Social Aspects of Machine Learning

Author Information

Ajil Jalal (University of Texas at Austin)
Sushrut Karmalkar (University of Texas at Austin)
Jessica Hoffmann (University of Texas at Austin)
Alexandros Dimakis (UT Austin)

Alex Dimakis is an Associate Professor at the Electrical and Computer Engineering department, University of Texas at Austin. He received his Ph.D. in electrical engineering and computer sciences from UC Berkeley. He received an ARO young investigator award in 2014, the NSF Career award in 2011, a Google faculty research award in 2012 and the Eli Jury dissertation award in 2008. He is the co-recipient of several best paper awards including the joint Information Theory and Communications Society Best Paper Award in 2012. His research interests include information theory, coding theory and machine learning.

Eric Price (UT-Austin)

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

More from the Same Authors