Explaining how your AI system is fair

by   Boris Ruf, et al.

To implement fair machine learning in a sustainable way, choosing the right fairness objective is key. Since fairness is a concept of justice which comes in various, sometimes conflicting definitions, this is not a trivial task though. The most appropriate fairness definition for an artificial intelligence (AI) system is a matter of ethical standards and legal requirements, and the right choice depends on the particular use case and its context. In this position paper, we propose to use a decision tree as means to explain and justify the implemented kind of fairness to the end users. Such a structure would first of all support AI practitioners in mapping ethical principles to fairness definitions for a concrete application and therefore make the selection a straightforward and transparent process. However, this approach would also help document the reasoning behind the decision making. Due to the general complexity of the topic of fairness in AI, we argue that specifying "fairness" for a given use case is the best way forward to maintain confidence in AI systems. In this case, this could be achieved by sharing the reasons and principles expressed during the decision making process with the broader audience.


page 1

page 2

page 3

page 4


Towards the Right Kind of Fairness in AI

Fairness is a concept of justice. Various definitions exist, some of the...

Getting Fairness Right: Towards a Toolbox for Practitioners

The potential risk of AI systems unintentionally embedding and reproduci...

On Consequentialism and Fairness

Recent work on fairness in machine learning has primarily emphasized how...

Fair navigation planning: a humanitarian robot use case

In this paper we investigate potential issues of fairness related to the...

Randomized Classifiers vs Human Decision-Makers: Trustworthy AI May Have to Act Randomly and Society Seems to Accept This

As artificial intelligence (AI) systems are increasingly involved in dec...

Disentangling and Operationalizing AI Fairness at LinkedIn

Operationalizing AI fairness at LinkedIn's scale is challenging not only...

RecSys Fairness Metrics: Many to Use But Which One To Choose?

In recent years, recommendation and ranking systems have become increasi...

Please sign up or login with your details

Forgot password? Click here to reset