The Use and Misuse of Counterfactuals in Ethical Machine Learning

by   Atoosa Kasirzadeh, et al.

The use of counterfactuals for considerations of algorithmic fairness and explainability is gaining prominence within the machine learning community and industry. This paper argues for more caution with the use of counterfactuals when the facts to be considered are social categories such as race or gender. We review a broad body of papers from philosophy and social sciences on social ontology and the semantics of counterfactuals, and we conclude that the counterfactual approach in machine learning fairness and social explainability can require an incoherent theory of what social categories are. Our findings suggest that most often the social categories may not admit counterfactual manipulation, and hence may not appropriately satisfy the demands for evaluating the truth or falsity of counterfactuals. This is important because the widespread use of counterfactuals in machine learning can lead to misleading results when applied in high-stakes domains. Accordingly, we argue that even though counterfactuals play an essential part in some causal inferences, their use for questions of algorithmic fairness and social explanations can create more problems than they resolve. Our positive result is a set of tenets about using counterfactuals for fairness and explanations in machine learning.



There are no comments yet.


page 1

page 2

page 3

page 4


Fairness and Robustness of Contrasting Explanations

Fairness and explainability are two important and closely related requir...

Impact Remediation: Optimal Interventions to Reduce Inequality

A significant body of research in the data sciences considers unfair dis...

Racial categories in machine learning

Controversies around race and machine learning have sparked debate among...

Theory In, Theory Out: The uses of social theory in machine learning for social science

Research at the intersection of machine learning and the social sciences...

The effects of algorithmic flagging on fairness: quasi-experimental evidence from Wikipedia

Online community moderators often rely on social signals like whether or...

Diversity and Inclusion Metrics in Subset Selection

The ethical concept of fairness has recently been applied in machine lea...

Theory In, Theory Out: How social theory can solve problems that machine learning can't

Research at the intersection of machine learning and the social sciences...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.