# Communication-Efficient Federated Learning with Binary Neural Networks

arXiv: https://arxiv.org/abs/2110.02226 · HTML: https://mlsanity.com/paper/2110.02226/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 5 Oct 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://mlsanity.com/paper/1804.05271/) (2018)
- [Sparse Communication for Distributed Gradient Descent](https://mlsanity.com/paper/1704.05021/) (2017)
- [Ternary Weight Networks](https://mlsanity.com/paper/1605.04711/) (2016)
- [Federated Optimization:Distributed Optimization Beyond the Datacenter](https://mlsanity.com/paper/1511.03575/) (2015)
- [Distributed Mean Estimation with Limited Communication](https://mlsanity.com/paper/1611.00429/) (2016)
- [Natural Compression for Distributed Deep Learning](https://mlsanity.com/paper/1905.10988/) (2019)
- [Ternary Compression for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2003.03564/) (2020)
- [Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequality](https://mlsanity.com/paper/1506.07216/) (2015)
- [Randomized Distributed Mean Estimation: Accuracy vs Communication](https://mlsanity.com/paper/1611.07555/) (2016)
- [Geometric Lower Bounds for Distributed Parameter Estimation under Communication Constraints](https://mlsanity.com/paper/1802.08417/) (2018)
- [Inference under Information Constraints I: Lower Bounds from Chi-Square Contraction](https://mlsanity.com/paper/1812.11476/) (2018)
- [Gradient Descent with Compressed Iterates](https://mlsanity.com/paper/1909.04716/) (2019)
- [Lower Bounds for Learning Distributions under Communication Constraints via Fisher Information](https://mlsanity.com/paper/1902.02890/) (2019)

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

- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Design](https://mlsanity.com/paper/2207.09387/) (2022)
- [On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks](https://mlsanity.com/paper/2111.07911/) (2021)
- [FedBAT: Communication-Efficient Federated Learning via Learnable Binarization](https://mlsanity.com/paper/2408.03215/) (2024)
- [Advancements in Federated Learning: Models, Methods, and Privacy](https://mlsanity.com/paper/2302.11466/) (2023)
- [How global observation works in Federated Learning: Integrating vertical training into Horizontal Federated Learning](https://mlsanity.com/paper/2112.01039/) (2021)
- [The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning](https://mlsanity.com/paper/2505.23176/) (2025)
- [Binary Federated Learning with Client-Level Differential Privacy](https://mlsanity.com/paper/2308.03320/) (2023)
- [Energy-Efficient Wireless Federated Learning via Doubly Adaptive Quantization](https://mlsanity.com/paper/2402.12957/) (2024)
- [CRS-FL: Conditional Random Sampling for Communication-Efficient and Privacy-Preserving Federated Learning](https://mlsanity.com/paper/2306.00674/) (2023)
- [P2U: Progressive Precision Update For Efficient Model Distribution](https://mlsanity.com/paper/2506.22871/) (2025)
- [Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference](https://mlsanity.com/paper/2603.15507/) (2026)
- [GQ-FSL: Green Quantized Federated Split Learning Framework for Wireless Edge Networks](https://mlsanity.com/paper/2607.29659/) (2026)
- [FedFit: Federated Fine-Tuning of LLMs via Vector-Bank Parameterization and Quantization](https://mlsanity.com/paper/2610.01537/) (2026)

## Abstract (arXiv)

Federated learning (FL) is a privacy-preserving machine learning setting that enables many devices to jointly train a shared global model without the need to reveal their data to a central server. However, FL involves a frequent exchange of the parameters between all the clients and the server that coordinates the training. This introduces extensive communication overhead, which can be a major bottleneck in FL with limited communication links. In this paper, we consider training the binary neural networks (BNN) in the FL setting instead of the typical real-valued neural networks to fulfill the stringent delay and efficiency requirement in wireless edge networks. We introduce a novel FL framework of training BNN, where the clients only upload the binary parameters to the server. We also propose a novel parameter updating scheme based on the Maximum Likelihood (ML) estimation that preserves the performance of the BNN even without the availability of aggregated real-valued auxiliary parameters that are usually needed during the training of the BNN. Moreover, for the first time in the literature, we theoretically derive the conditions under which the training of BNN is converging. { Numerical results show that the proposed FL framework significantly reduces the communication cost compared to the conventional neural networks with typical real-valued parameters, and the performance loss incurred by the binarization can be further compensated by a hybrid method.