Proposes a formal DP-compatible framework with three unfairness measures (mutual information with TV proxy, MaxSAT-based repair, top-k tuple contribution) that satisfy positivity, monotonicity, and computability.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
FASE pairs a spatiotemporal graph neural network and multivariate Hawkes process for crime prediction with a fairness-constrained linear program for patrol allocation, showing that allocation fairness holds in simulation but a 3.5 percentage point detection gap between minority and non-minority ZIPs
citing papers explorer
-
Measuring Database Unfairness via Dependency Quantification Under Differential Privacy
Proposes a formal DP-compatible framework with three unfairness measures (mutual information with TV proxy, MaxSAT-based repair, top-k tuple contribution) that satisfy positivity, monotonicity, and computability.
-
FASE : A Fairness-Aware Spatiotemporal Event Graph Framework for Predictive Policing
FASE pairs a spatiotemporal graph neural network and multivariate Hawkes process for crime prediction with a fairness-constrained linear program for patrol allocation, showing that allocation fairness holds in simulation but a 3.5 percentage point detection gap between minority and non-minority ZIPs