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

arXiv: https://arxiv.org/abs/2106.00275 · HTML: https://mlsanity.com/paper/2106.00275/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 1 Jun 2021.

## Builds on (most cited first, 12 of 12)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [FetchSGD: Communication-Efficient Federated Learning with Sketching](https://mlsanity.com/paper/2007.07682/) (2020)
- [Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating](https://mlsanity.com/paper/2103.00958/) (2021)

## Built on by (most cited first, 14 of 14)

- [A Survey on Gradient Inversion: Attacks, Defenses and Future Directions](https://mlsanity.com/paper/2206.07284/) (2022)
- [Advances and Open Challenges in Federated Foundation Models](https://mlsanity.com/paper/2404.15381/) (2024)
- [A Survey on Efficient Federated Learning Methods for Foundation Model Training](https://mlsanity.com/paper/2401.04472/) (2024)
- [Accelerated Federated Learning with Decoupled Adaptive Optimization](https://mlsanity.com/paper/2207.07223/) (2022)
- [FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learning](https://mlsanity.com/paper/2208.02442/) (2022)
- [Hierarchical Federated Learning with Multi-Timescale Gradient Correction](https://mlsanity.com/paper/2409.18448/) (2024)
- [A Fair Federated Learning Framework With Reinforcement Learning](https://mlsanity.com/paper/2205.13415/) (2022)
- [Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspective](https://mlsanity.com/paper/2405.20431/) (2024)
- [WW-FL: Secure and Private Large-Scale Federated Learning](https://mlsanity.com/paper/2302.09904/) (2023)
- [FedCAT: Towards Accurate Federated Learning via Device Concatenation](https://mlsanity.com/paper/2202.12751/) (2022)
- [Personalized Federated Learning with Hidden Information on Personalized Prior](https://mlsanity.com/paper/2211.10684/) (2022)
- [Sequential Federated Learning in Hierarchical Architecture on Non-IID Datasets](https://mlsanity.com/paper/2408.09762/) (2024)
- [Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights](https://mlsanity.com/paper/2509.05142/) (2025)
- [Federated Geometric Monte Carlo Clustering to Counter Non-IID Datasets](https://mlsanity.com/paper/2204.11017/) (2022)

## Abstract (arXiv)

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.