Fairness for Image Generation with Uncertain Sensitive Attributes

Ajil Jalal, Sushrut Karmalkar, Jessica Hoffmann, Alex Dimakis, Eric Price
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4721-4732, 2021.

Abstract

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 being “unfair” 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-jalal21b, title = {Fairness for Image Generation with Uncertain Sensitive Attributes}, author = {Jalal, Ajil and Karmalkar, Sushrut and Hoffmann, Jessica and Dimakis, Alex and Price, Eric}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {4721--4732}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/jalal21b/jalal21b.pdf}, url = {https://proceedings.mlr.press/v139/jalal21b.html}, abstract = {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 being “unfair” 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.} }
Endnote
%0 Conference Paper %T Fairness for Image Generation with Uncertain Sensitive Attributes %A Ajil Jalal %A Sushrut Karmalkar %A Jessica Hoffmann %A Alex Dimakis %A Eric Price %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-jalal21b %I PMLR %P 4721--4732 %U https://proceedings.mlr.press/v139/jalal21b.html %V 139 %X 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 being “unfair” 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.
APA
Jalal, A., Karmalkar, S., Hoffmann, J., Dimakis, A. & Price, E.. (2021). Fairness for Image Generation with Uncertain Sensitive Attributes. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:4721-4732 Available from https://proceedings.mlr.press/v139/jalal21b.html.

Related Material