FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification

2026-03-06

AI Summary

This work addresses the limitations of existing federated domain generalization methods for person re-identification, which rely on global features and uniform aggregation, thereby failing to capture fine-grained domain-invariant local information and ignoring heterogeneity in clients’ feature extraction capabilities. To overcome these challenges, we propose FedARKS, a novel framework that integrates a Robust Knowledge (RK) mechanism to jointly extract discriminative local and global features, enhancing fine-grained representation learning. Additionally, FedARKS introduces a Knowledge Selection (KS) mechanism that dynamically weights and aggregates high-quality knowledge from clients based on their individual capabilities, moving beyond the constraints of simple averaging. Experimental results demonstrate that FedARKS significantly improves model generalization to unseen domains while preserving data privacy.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

The application of federated domain generalization in person re-identification (FedDG-ReID) aims to enhance the model's generalization ability in unseen domains while protecting client data privacy. However, existing mainstream methods typically rely on global feature representations and simple averaging operations for model aggregation, leading to two limitations in domain generalization: (1) Using only global features makes it difficult to capture subtle, domain-invariant local details (such as accessories or textures); (2) Uniform parameter averaging treats all clients as equivalent, ignoring their differences in robust feature extraction capabilities, thereby diluting the contributions of high quality clients. To address these issues, we propose a novel federated learning framework, Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration (FedARKS), comprising two mechanisms: RK (Robust Knowledge) and KS (Knowledge Selection).

Problem

• federated learning
• person re-identification
• domain generalization
• feature representation
• model aggregation

Innovation

• Federated Learning
• Person Re-identification
• Domain Generalization
• Knowledge Selection
• Robust Feature Aggregation