Enforcing Delayed-Impact Fairness Guarantees
This addresses fairness in critical applications like education and lending, offering a novel approach to prevent long-term harm to disadvantaged groups.
The paper tackles the problem of machine learning models increasing social inequality over time by introducing ELF, the first classification algorithm that provides high-confidence fairness guarantees for long-term impact, with proven bounds on unfairness probability and experimental validation of mitigation.
Recent research has shown that seemingly fair machine learning models, when used to inform decisions that have an impact on peoples' lives or well-being (e.g., applications involving education, employment, and lending), can inadvertently increase social inequality in the long term. This is because prior fairness-aware algorithms only consider static fairness constraints, such as equal opportunity or demographic parity. However, enforcing constraints of this type may result in models that have negative long-term impact on disadvantaged individuals and communities. We introduce ELF (Enforcing Long-term Fairness), the first classification algorithm that provides high-confidence fairness guarantees in terms of long-term, or delayed, impact. We prove that the probability that ELF returns an unfair solution is less than a user-specified tolerance and that (under mild assumptions), given sufficient training data, ELF is able to find and return a fair solution if one exists. We show experimentally that our algorithm can successfully mitigate long-term unfairness.