Privacy-Preserving Feature Valuation in Vertical Federated Learning Using Shapley-CMI and PSI Permutation

📅 2025-12-16
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
In vertical federated learning (VFL), securely and fairly evaluating feature contributions remains challenging under model-agnostic assumptions, especially without access to raw data or shared model training. Method: This paper proposes the first privacy-preserving Shapley-CMI framework, integrating Shapley values with conditional mutual information (CMI) to enable model-agnostic, data- and training-free feature valuation. We design an encrypted permutation and intersection-size computation protocol based on private set intersection (PSI) servers, achieving fully decentralized, trustless implementation. To enhance efficiency, we introduce ID-based grouping discretization and lightweight homomorphic operations. Contributions/Results: Extensive experiments validate the framework’s correctness, end-to-end privacy guarantees, and scalability across multi-party VFL settings. Our approach establishes an auditable, interpretable foundation for fair feature valuation in early-stage VFL data collaboration—without requiring raw data sharing, model exchange, or a trusted third party.

Technology Category

Application Category

📝 Abstract
Federated Learning (FL) is an emerging machine learning paradigm that enables multiple parties to collaboratively train models without sharing raw data, ensuring data privacy. In Vertical FL (VFL), where each party holds different features for the same users, a key challenge is to evaluate the feature contribution of each party before any model is trained, particularly in the early stages when no model exists. To address this, the Shapley-CMI method was recently proposed as a model-free, information-theoretic approach to feature valuation using Conditional Mutual Information (CMI). However, its original formulation did not provide a practical implementation capable of computing the required permutations and intersections securely. This paper presents a novel privacy-preserving implementation of Shapley-CMI for VFL. Our system introduces a private set intersection (PSI) server that performs all necessary feature permutations and computes encrypted intersection sizes across discretized and encrypted ID groups, without the need for raw data exchange. Each party then uses these intersection results to compute Shapley-CMI values, computing the marginal utility of their features. Initial experiments confirm the correctness and privacy of the proposed system, demonstrating its viability for secure and efficient feature contribution estimation in VFL. This approach ensures data confidentiality, scales across multiple parties, and enables fair data valuation without requiring the sharing of raw data or training models.
Problem

Research questions and friction points this paper is trying to address.

Evaluates feature contributions in vertical federated learning without sharing raw data
Provides a privacy-preserving implementation of Shapley-CMI using PSI and encryption
Enables secure and efficient feature valuation before model training in VFL
Innovation

Methods, ideas, or system contributions that make the work stand out.

PSI server for secure feature permutations
Shapley-CMI for model-free feature valuation
Encrypted intersection sizes without raw data exchange
U
Unai Laskurain
Electronics and Computing Department, Mondragon Unibertsitatea, Arrasate-Mondragon, Spain
A
Aitor Aguirre-Ortuzar
Electronics and Computing Department, Mondragon Unibertsitatea, Arrasate-Mondragon, Spain
U
Urko Zurutuza
Electronics and Computing Department, Mondragon Unibertsitatea, Arrasate-Mondragon, Spain