Toward Individual Fairness Without Centralized Data: Selective Counterfactual Consistency for Vertical Federated Learning

TL;DR

This paper introduces SCC-VFL, a privacy-preserving framework for individual fairness in vertical federated learning, ensuring prediction stability under protected attribute interventions without centralized data.

Contribution

It proposes a novel server-centric method combining private feature role discovery, masked counterfactual generation, and enforcement loss to achieve individual fairness in VFL.

Findings

Reduces decision flip rates by up to 98% compared to baselines.

Maintains or improves predictive accuracy.

Enhances robustness and lowers attribute-inference attack success.

Abstract

When algorithmic decisions depend on data distributed across institutions, how can we ensure that an individual's outcome does not change arbitrarily based on a protected attribute? We study this question in vertical federated learning (VFL), where features are split across parties, sensitive attributes may be private, and proxies for protected characteristics can be scattered across institutional boundaries under strict privacy constraints. Our focus is on individual-level counterfactual stability, i.e., per-instance prediction consistency under protected-attribute interventions as formalized in the causal fairness literature, rather than group parity guarantees such as demographic parity or equalized odds. We propose SCC-VFL, a server-centric framework for enforcing selective counterfactual consistency (SCC) at the individual level in VFL. SCC-VFL operationalizes a given policy specification by combining three components: (i) differentially private, graph-free discovery of feature roles into non-descendants, policy-permitted mediators, and impermissible proxies using only a formally private sketch of the sensitive attribute, with a formal per-release privacy that does not extend to the full training pipeline; (ii) masked counterfactual generation that edits only mediators while fixing non-descendants and suppressing proxy leakage; and (iii) server-side enforcement via an SCC consistency loss that penalizes impermissible prediction changes under protected-attribute interventions. Across three real-world datasets spanning credit, healthcare, and criminal justice, SCC-VFL maintains or improves predictive accuracy while sharply reducing decision flip rates by up to 98% relative to strong baselines. It also lowers attribute-inference attack success and improves robustness, demonstrating favorable utility-fairness-privacy trade-offs in realistic VFL deployments.