SCALES: From Fairness Principles to Constrained Decision-Making
This work addresses fairness in decision-making for AI systems, but it is incremental as it builds on existing fairness principles and CMDPs.
The authors tackled the problem of translating fairness principles into constrained decision-making by proposing SCALES, a framework that encodes fairness as constraints in a Constraint Markov Decision Process, and demonstrated it produces fair policies in simulated healthcare and COMPAS dataset scenarios.
This paper proposes SCALES, a general framework that translates well-established fairness principles into a common representation based on the Constraint Markov Decision Process (CMDP). With the help of causal language, our framework can place constraints on both the procedure of decision making (procedural fairness) as well as the outcomes resulting from decisions (outcome fairness). Specifically, we show that well-known fairness principles can be encoded either as a utility component, a non-causal component, or a causal component in a SCALES-CMDP. We illustrate SCALES using a set of case studies involving a simulated healthcare scenario and the real-world COMPAS dataset. Experiments demonstrate that our framework produces fair policies that embody alternative fairness principles in single-step and sequential decision-making scenarios.