H-FL: A Hierarchical Communication-Efficient and Privacy-Protected Architecture for Federated Learning

2021/06/01 by Yang He, He Yang, Yang, He · 1 citation
Computer Science · #Advanced Neural Network Applications #Cryptography and Data Security #Cryptography and Security (cs.CR) #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #Privacy-Preserving Technologies in Data #and Cluster Computing (cs.DC) #cs.CR #cs.DC #cs.LG

paper · pdf · doi:10.48550/arxiv.2106.00275

Accepted by IJCAI 2021, 7pages, 10 figures

arxiv created 2021/06/01 · openalex publication_date 2021/06/01 · arxiv updated 2021/06/02 · openalex created_date 2021/06/22 · openalex updated_date 2026/07/28

Abstract

The longstanding goals of federated learning (FL) require rigorous privacy guarantees and low communication overhead while holding a relatively high model accuracy. However, simultaneously achieving all the goals is extremely challenging. In this paper, we propose a novel framework called hierarchical federated learning (H-FL) to tackle this challenge. Considering the degradation of the model performance due to the statistic heterogeneity of the training data, we devise a runtime distribution reconstruction strategy, which reallocates the clients appropriately and utilizes mediators to rearrange the local training of the clients. In addition, we design a compression-correction mechanism incorporated into H-FL to reduce the communication overhead while not sacrificing the model performance. To further provide privacy guarantees, we introduce differential privacy while performing local training, which injects moderate amount of noise into only part of the complete model. Experimental results show that our H-FL framework achieves the state-of-art performance on different datasets for the real-world image recognition tasks.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Gradient-based learning applied to document recognition
• Federated Learning With Differential Privacy: Algorithms and Performance Analysis
• Learning Multiple Layers of Features from Tiny Images
• Advances and Open Problems in Federated Learning

Cited by

• Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights

Related

• FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
• Privacy-Preserving Federated Learning with Consistency via Knowledge Distillation Using Conditional Generator
• Privacy-Preserving Self-Taught Federated Learning for Heterogeneous Data
• DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning
• Better Methods and Theory for Federated Learning: Compression, Client Selection and Heterogeneity