The use and misuse of counterfactuals in ethical machine learning

A. Kasirzadeh, A. Smart

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationFACCT '21
Subtitle of host publicationProceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency
PublisherAssociation for Computing Machinery (ACM)
Number of pages9
ISBN (Electronic)9781450383097
Publication statusPublished - Mar 2021
Event4th ACM Conference on Fairness, Accountability, and Transparency: FAccT 2021 - Virtual, Online
Duration: 3 Mar 202110 Mar 2021
Conference number: 167464


Conference4th ACM Conference on Fairness, Accountability, and Transparency

Keywords / Materials (for Non-textual outputs)

  • ethics of AI
  • ethical AI
  • counterfactuals
  • machine learning
  • fairness
  • algorithmic fairness
  • explanation
  • explainable AI
  • philosophy
  • social ontology
  • social category
  • social kind
  • philosophy of AI


Dive into the research topics of 'The use and misuse of counterfactuals in ethical machine learning'. Together they form a unique fingerprint.

Cite this