# Accelerating Energy-Efficient Federated Learning in Cell-Free Networks with Adaptive Quantization

arXiv: https://arxiv.org/abs/2412.20785 · HTML: https://mlsanity.com/paper/2412.20785/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 30 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Energy Efficient Federated Learning Over Wireless Communication Networks](https://mlsanity.com/paper/1911.02417/) (2019)
- [Decentralized Federated Averaging](https://mlsanity.com/paper/2104.11375/) (2021)
- [Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2102.04487/) (2021)
- [Wireless Communications for Collaborative Federated Learning](https://mlsanity.com/paper/2006.02499/) (2020)
- [DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning](https://mlsanity.com/paper/2111.00465/) (2021)
- [Cell-Free Massive MIMO for Wireless Federated Learning](https://mlsanity.com/paper/1909.12567/) (2019)
- [Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup](https://mlsanity.com/paper/2308.00522/) (2023)
- [FedDQ: Communication-Efficient Federated Learning with Descending Quantization](https://mlsanity.com/paper/2110.02291/) (2021)
- [Foundations of User-Centric Cell-Free Massive MIMO](https://mlsanity.com/paper/2108.02541/) (2021)
- [SAFARI: Sparsity enabled Federated Learning with Limited and Unreliable Communications](https://mlsanity.com/paper/2204.02321/) (2022)
- [More Communication Does Not Result in Smaller Generalization Error in Federated Learning](https://mlsanity.com/paper/2304.12216/) (2023)
- [AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategy](https://mlsanity.com/paper/2308.00258/) (2023)
- [Energy-Efficient Power Control: A Look at 5G Wireless Technologies](https://mlsanity.com/paper/1503.04609/) (2015)
- [FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization](https://mlsanity.com/paper/2406.18156/) (2024)
- [FedCau: A Proactive Stop Policy for Communication and Computation Efficient Federated Learning](https://mlsanity.com/paper/2204.07773/) (2022)
- [A-LAQ: Adaptive Lazily Aggregated Quantized Gradient](https://mlsanity.com/paper/2210.17474/) (2022)
- [Joint Compression and Deadline Optimization for Wireless Federated Learning](https://mlsanity.com/paper/2305.03969/) (2023)
- [Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMO](https://mlsanity.com/paper/2212.06482/) (2022)
- [Joint Energy and Latency Optimization in Federated Learning over Cell-Free Massive MIMO Networks](https://mlsanity.com/paper/2404.18287/) (2024)
- [Adaptive Quantization Resolution and Power Control for Federated Learning over Cell-free Networks](https://mlsanity.com/paper/2412.10878/) (2024)

## Built on by (most cited first, 1 of 1)

- [Mitigating Heterogeneity-Induced Drift in Hierarchical Sign-Based Federated Learning](https://mlsanity.com/paper/2602.02355/) (2026)

## Abstract (arXiv)

Federated Learning (FL) enables clients to share learning parameters instead of local data, reducing communication overhead. Traditional wireless networks face latency challenges with FL. In contrast, Cell-Free Massive MIMO (CFmMIMO) can serve multiple clients on shared resources, boosting spectral efficiency and reducing latency for large-scale FL. However, clients' communication resource limitations can hinder the completion of the FL training. To address this challenge, we propose an energy-efficient, low-latency FL framework featuring optimized uplink power allocation for seamless client-server collaboration. Our framework employs an adaptive quantization scheme, dynamically adjusting bit allocation for local gradient updates to reduce communication costs. We formulate a joint optimization problem covering FL model updates, local iterations, and power allocation, solved using sequential quadratic programming (SQP) to balance energy and latency. Additionally, clients use the AdaDelta method for local FL model updates, enhancing local model convergence compared to standard SGD, and we provide a comprehensive analysis of FL convergence with AdaDelta local updates. Numerical results show that, within the same energy and latency budgets, our power allocation scheme outperforms the Dinkelbach and max-sum rate methods by increasing the test accuracy up to 7% and 19%, respectively. Moreover, for the three power allocation methods, our proposed quantization scheme outperforms AQUILA and LAQ by increasing test accuracy by up to 36% and 35%, respectively.