Energy Shields for Fairness
About
Runtime fairness is not a one-time constraint but a dynamic property evaluated over a sequence of decisions. To ensure fairness at runtime, it is necessary to account for past decisions, information neglected by conventional, static classifiers. Traditional fairness shields enforce runtime fairness abruptly, by intervening \emph{deterministically} whenever a sequence of decisions violates the target for a running fairness measure. This motivates our \emph{main conceptual contribution: \textbf{energy shields}.} An energy shield is a novel, lightweight, adaptive controller that monitors a sequence of decisions and intervenes \emph{probabilistically} to ensure runtime fairness smoothly, by utilizing physics-inspired energy functions to nudge the sequence toward fairness: the more unfair the decisions, the stronger the nudging force becomes. This makes energy shields the \emph{\textbf{first}} fairness shields to provide both \emph{short-term safety and long-term liveness guarantees}. Safety ensures that the running fairness measure stays within a running target interval with high probability, and liveness ensures that the limit of the fairness measure lies within the limit target interval. Intuitively, the short-term specifies the tolerated fairness values and the long-term specifies the desired fairness values. We also provide a synthesis procedure for constructing the least intrusive energy shield for a given target specification, and demonstrate its efficiency experimentally. We evaluate our energy shields against existing fairness shields through the lens of short- and long-term fairness.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Fairness-aware Classification | COMPAS Race (test) | DP1.8 | 14 | |
| Group Fairness | Adult Income Race | Demographic Parity0.01 | 9 | |
| Group Fairness | Adult Income Gender | Demographic Parity0.004 | 9 | |
| Group Fairness | German Credit Age | Demographic Parity0.005 | 9 | |
| Group Fairness | COMPAS Gender | Demographic Parity0.8 | 9 | |
| Fair Decision Making | COMPAS Gender 34 (test) | Total Interventions29.4 | 9 | |
| Fair Decision Making | Adult Income Race 11 (test) | Total Interventions16.2 | 9 | |
| Group Fairness | German Credit Gender | Demographic Parity0.052 | 9 | |
| Fair Decision Making | German Credit Gender 30 (test) | Total Interventions1.2 | 9 | |
| Fair Decision Making | Adult Income Gender 11 (test) | Total Interventions29.6 | 9 |