Causal Modeling for Fairness In Dynamical Systems

Elliot Creager, David Madras, Toniann Pitassi, Richard Zemel
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2185-2195, 2020.

Abstract

In many applications areas—lending, education, and online recommenders, for example—fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both immediate and long-term effects for individuals and demographic groups. We discuss causal directed acyclic graphs (DAGs) as a unifying framework for the recent literature on fairness in such dynamical systems. We show that this formulation affords several new directions of inquiry to the modeler, where sound causal assumptions can be expressed and manipulated. We emphasize the importance of computing interventional quantities in the dynamical fairness setting, and show how causal assumptions enable simulation (when environment dynamics are known) and estimation by adjustment (when dynamics are unknown) of intervention on short- and long-term outcomes, at both the group and individual levels.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-creager20a, title = {Causal Modeling for Fairness In Dynamical Systems}, author = {Creager, Elliot and Madras, David and Pitassi, Toniann and Zemel, Richard}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {2185--2195}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/creager20a/creager20a.pdf}, url = {https://proceedings.mlr.press/v119/creager20a.html}, abstract = {In many applications areas—lending, education, and online recommenders, for example—fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both immediate and long-term effects for individuals and demographic groups. We discuss causal directed acyclic graphs (DAGs) as a unifying framework for the recent literature on fairness in such dynamical systems. We show that this formulation affords several new directions of inquiry to the modeler, where sound causal assumptions can be expressed and manipulated. We emphasize the importance of computing interventional quantities in the dynamical fairness setting, and show how causal assumptions enable simulation (when environment dynamics are known) and estimation by adjustment (when dynamics are unknown) of intervention on short- and long-term outcomes, at both the group and individual levels.} }
Endnote
%0 Conference Paper %T Causal Modeling for Fairness In Dynamical Systems %A Elliot Creager %A David Madras %A Toniann Pitassi %A Richard Zemel %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-creager20a %I PMLR %P 2185--2195 %U https://proceedings.mlr.press/v119/creager20a.html %V 119 %X In many applications areas—lending, education, and online recommenders, for example—fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both immediate and long-term effects for individuals and demographic groups. We discuss causal directed acyclic graphs (DAGs) as a unifying framework for the recent literature on fairness in such dynamical systems. We show that this formulation affords several new directions of inquiry to the modeler, where sound causal assumptions can be expressed and manipulated. We emphasize the importance of computing interventional quantities in the dynamical fairness setting, and show how causal assumptions enable simulation (when environment dynamics are known) and estimation by adjustment (when dynamics are unknown) of intervention on short- and long-term outcomes, at both the group and individual levels.
APA
Creager, E., Madras, D., Pitassi, T. & Zemel, R.. (2020). Causal Modeling for Fairness In Dynamical Systems. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:2185-2195 Available from https://proceedings.mlr.press/v119/creager20a.html.

Related Material