FedHAP: Federated Hashing With Global Prototypes for Cross-Silo Retrieval

作     者：Yang, Meilin Xu, Jian Ding, Wenbo Liu, Yang 

作者机构：Tsinghua Univ Tsinghua Berkeley Shenzhen Inst Tsinghua Shenzhen Int Grad Sch Beijing 100190 Peoples R China V Int Open Source Lab RISC Tsinghua Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 201210 Peoples R China Tsinghua Univ Inst AI Ind Res AIR Beijing 100190 Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS》 (IEEE Trans Parallel Distrib Syst)

年 卷 期：2024年第35卷第4期

页      面：592-603页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Key R#x0026 D Program of China 

主　　题：Federated learning information retrieval deep hashing 

摘      要：Deep hashing has been widely applied in large-scale data retrieval due to its superior retrieval efficiency and low storage cost. However, data are often scattered in data silos with privacy concerns, so performing centralized data storage and retrieval is not always possible. Leveraging the approach of federated learning (FL) to perform deep hashing is a recent research trend. However, existing frameworks mostly rely on the aggregation of the local deep hashing models, which are trained by performing similarity learning with local skewed data only. Therefore, they cannot work well for non-IID clients in a real federated environment. To overcome these challenges, we propose a novel federated hashing framework that enables participating clients to jointly train a shared deep hashing model by leveraging the class-wise prototypical hash codes. Globally, sharing global prototypes with only one prototypical hash code per class assists in learning consistent code distributions across clients while minimizing the cost of communication and privacy. Locally, the use of the global prototypical hash codes are maximized by jointly training a discriminator network and the local hashing network. Extensive experiments on benchmark datasets are conducted to demonstrate that our method can significantly improve the performance of the deep hashing model in the federated environments with non-IID data distributions.