Beyond Independent Manipulation: Individual Fairness-aware Strategic Classification with Peer Imitation

2026-05-30

AI Summary

This work addresses a critical limitation in traditional strategic classification methods, which assume individuals independently manipulate their features and thereby overlook the individual fairness principle that similar individuals should receive similar outcomes. To capture the interdependent strategic behaviors induced by fairness considerations, the paper proposes the Individual Fairness-aware Strategic Classification (IFSC) framework—the first to integrate individual fairness into strategic classification. IFSC models agents as strategically imitating nearby accepted peers based on similarity, and learns a classifier under the resulting manipulated data distribution. To account for uncertainty in observing peers’ outcomes, the framework incorporates stochastic perturbations, enabling robust learning. Experiments on both synthetic and real-world datasets demonstrate that IFSC significantly improves individual fairness consistency while effectively mitigating distributional distortions caused by imitation behavior.

Abstract

Strategic classification (SC) investigates scenarios where agents manipulate their features to obtain favorable decisions from predictive models. Existing fairness-aware SC approaches primarily focus on group fairness and typically assume that agents respond independently. However, when individual fairness is required, ensuring similar individuals receive similar outcomes, agents' manipulation becomes interdependent: an agent's preferred manipulation depends on the neighborhoods' outcomes. This induces a mismatch between classical SC formulations and fairness-aware decision settings, where independent models no longer accurately characterize strategic manipulations. To address this issue, we introduce individual fairness-aware strategic classification (IFSC), a framework that models peer-driven manipulation arising from individual fairness, where agents imitate nearby positively decided peers to obtain favorable outcomes. IFSC characterizes strategic manipulation as similarity-based imitation toward visible accepted peers and learns classifiers under the resulting post-manipulation distributions. To account for uncertainty in peer observability, IFSC employs a robust learning process that introduces stochastic perturbations during manipulation simulation. Experiments on synthetic and real-world datasets demonstrate that IFSC improves individual-fairness consistency and mitigates imitation-induced distortions.

Problem

• strategic classification
• individual fairness
• peer imitation
• interdependent manipulation
• fairness-aware decision making

Innovation

• individual fairness
• strategic classification
• peer imitation
• fairness-aware learning
• robust optimization