# Communication Efficient Federated Learning with Linear Convergence on Heterogeneous Data

arXiv: https://arxiv.org/abs/2503.15804 · HTML: https://mlsanity.com/paper/2503.15804/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 20 Mar 2025.

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

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Bayesian Nonparametric Federated Learning of Neural Networks](https://mlsanity.com/paper/1905.12022/) (2019)
- [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://mlsanity.com/paper/1909.13014/) (2019)
- [A Joint Learning and Communications Framework for Federated Learning over Wireless Networks](https://mlsanity.com/paper/1909.07972/) (2019)
- [Federated Learning for Internet of Things: A Comprehensive Survey](https://mlsanity.com/paper/2104.07914/) (2021)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [Federated Learning with Compression: Unified Analysis and Sharp Guarantees](https://mlsanity.com/paper/2007.01154/) (2020)
- [Scheduling Policies for Federated Learning in Wireless Networks](https://mlsanity.com/paper/1908.06287/) (2019)
- [Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients](https://mlsanity.com/paper/2102.07053/) (2021)
- [FedSplit: An algorithmic framework for fast federated optimization](https://mlsanity.com/paper/2005.05238/) (2020)
- [From Local SGD to Local Fixed-Point Methods for Federated Learning](https://mlsanity.com/paper/2004.01442/) (2020)
- [Revisiting Weighted Aggregation in Federated Learning with Neural Networks](https://mlsanity.com/paper/2302.10911/) (2023)
- [On Safeguarding Privacy and Security in the Framework of Federated Learning](https://mlsanity.com/paper/1909.06512/) (2019)
- [Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning](https://mlsanity.com/paper/2103.05032/) (2021)
- [A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates](https://mlsanity.com/paper/1704.07807/) (2017)
- [Federated Learning for Internet of Things: Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2111.07494/) (2021)
- [Federated Learning with Spiking Neural Networks](https://mlsanity.com/paper/2106.06579/) (2021)
- [Decentralized Stochastic Optimization with Inherent Privacy Protection](https://mlsanity.com/paper/2205.03884/) (2022)
- [Adaptive Federated Learning with Auto-Tuned Clients](https://mlsanity.com/paper/2306.11201/) (2023)
- [Locally Adaptive Federated Learning](https://mlsanity.com/paper/2307.06306/) (2023)

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

- [Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations](https://mlsanity.com/paper/2604.12968/) (2026)

## Abstract (arXiv)

By letting local clients perform multiple local updates before communicating with a parameter server, modern federated learning algorithms such as FedAvg tackle the communication bottleneck problem in distributed learning and have found many successful applications. However, this asynchrony between local updates and communication also leads to a ''client-drift'' problem when the data is heterogeneous (not independent and identically distributed), resulting in errors in the final learning result. In this paper, we propose a federated learning algorithm, which is called FedCET, to ensure accurate convergence even under heterogeneous distributions of data across clients. Inspired by the distributed optimization algorithm NIDS, we use learning rates to weight information received from local clients to eliminate the ''client-drift''. We prove that under appropriate learning rates, FedCET can ensure linear convergence to the exact solution. Different from existing algorithms which have to share both gradients and a drift-correction term to ensure accurate convergence under heterogeneous data distributions, FedCET only shares one variable, which significantly reduces communication overhead. Numerical comparison with existing counterpart algorithms confirms the effectiveness of FedCET.