FedPalm: A General Federated Learning Framework for Closed- and Open-Set Palmprint Verification

2025-03-05

AI Summary

Palmprint verification faces critical privacy challenges—including biometric data sensitivity, non-shareability, and severe client-side data heterogeneity—rendering conventional centralized learning infeasible. Method: We establish the first federated learning benchmark supporting both closed-set and open-set verification. Our approach introduces a dual-expert collaborative architecture (a local texture expert and a globally shared expert) coupled with a learnable texture interaction module, enabling dynamic balance between personalization and generalization via feature routing and cross-expert relational modeling. Contribution/Results: Comprehensive evaluation across diverse federated settings on a unified benchmark demonstrates significant improvements in verification accuracy and robustness. This work bridges two key gaps in federated palmprint recognition: the absence of standardized evaluation protocols and effective personalization mechanisms. It delivers a reproducible, scalable technical paradigm for privacy-preserving biometric authentication.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Current deep learning (DL)-based palmprint verification models rely on centralized training with large datasets, which raises significant privacy concerns due to biometric data's sensitive and immutable nature. Federated learning~(FL), a privacy-preserving distributed learning paradigm, offers a compelling alternative by enabling collaborative model training without the need for data sharing. However, FL-based palmprint verification faces critical challenges, including data heterogeneity from diverse identities and the absence of standardized evaluation benchmarks. This paper addresses these gaps by establishing a comprehensive benchmark for FL-based palmprint verification, which explicitly defines and evaluates two practical scenarios: closed-set and open-set verification. We propose FedPalm, a unified FL framework that balances local adaptability with global generalization. Each client trains a personalized textural expert tailored to local data and collaboratively contributes to a shared global textural expert for extracting generalized features. To further enhance verification performance, we introduce a Textural Expert Interaction Module that dynamically routes textural features among experts to generate refined side textural features. Learnable parameters are employed to model relationships between original and side features, fostering cross-texture-expert interaction and improving feature discrimination. Extensive experiments validate the effectiveness of FedPalm, demonstrating robust performance across both scenarios and providing a promising foundation for advancing FL-based palmprint verification research.

Problem

• Privacy concerns in centralized palmprint verification models.
• Challenges in FL-based palmprint verification due to data heterogeneity.
• Lack of standardized benchmarks for FL-based palmprint verification.

Innovation

• Federated Learning for privacy-preserving palmprint verification
• Personalized and shared textural experts for feature extraction
• Dynamic Textural Expert Interaction Module for enhanced performance