Algorithmic Fairness: A Runtime Perspective
This work addresses the challenge of ensuring fairness in real-world AI systems that operate dynamically over time, representing an incremental contribution by extending static fairness concepts to runtime analysis.
The paper tackles the problem of analyzing fairness in AI systems as a runtime property, rather than a static one, by proposing a framework based on sequences of coin tosses with evolving biases, and provides general results for monitoring and enforcing fairness under various assumptions.
Fairness in AI is traditionally studied as a static property evaluated once, over a fixed dataset. However, real-world AI systems operate sequentially, with outcomes and environments evolving over time. This paper proposes a framework for analysing fairness as a runtime property. Using a minimal yet expressive model based on sequences of coin tosses with possibly evolving biases, we study the problems of monitoring and enforcing fairness expressed in either toss outcomes or coin biases. Since there is no one-size-fits-all solution for either problem, we provide a summary of monitoring and enforcement strategies, parametrised by environment dynamics, prediction horizon, and confidence thresholds. For both problems, we present general results under simple or minimal assumptions. We survey existing solutions for the monitoring problem for Markovian and additive dynamics, and existing solutions for the enforcement problem in static settings with known dynamics.