Fedhap: Federated Hashing With Global Prototypes For Cross-silo Retrieval

Abstract

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 concept 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 the shared deep hashing model by leveraging the prototypical hash codes for each class. Globally, the transmission of global prototypes with only one prototypical hash code per class will minimize the impact of communication cost

Stats

• citations10
• S2 citations—
• github stars0
• HF likes0
• heat score7.81
• arxiv keyyang2022fedhap

Related papers

• Deep Lifelong Cross-modal Hashing (2023)6.34
• Fusion-supervised Deep Cross-modal Hashing (2019)8.60
• Deep Class-guided Hashing For Multi-label Cross-modal Retrieval (2024)6.20
• FDDH: Fast Discriminative Discrete Hashing For Large-scale Cross-modal Retrieval (2021)15.50
• Weakly-paired Cross-modal Hashing (2019)0.00
• SSDH: Semi-supervised Deep Hashing For Large Scale Image Retrieval (2016)15.40
• Mutual Learning For Hashing: Unlocking Strong Hash Functions From Weak Supervision (2025)0.00
• Deep Cross-modal Hashing With Hashing Functions And Unified Hash Codes Jointly Learning (2019)14.23