# Fast-Convergent Federated Learning via Cyclic Aggregation

arXiv: https://arxiv.org/abs/2210.16520 · HTML: https://mlsanity.com/paper/2210.16520/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 29 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges](https://mlsanity.com/paper/2009.13012/) (2020)
- [Federated Learning for Wireless Communications: Motivation, Opportunities and Challenges](https://mlsanity.com/paper/1908.06847/) (2019)
- [On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimization](https://mlsanity.com/paper/1708.01012/) (2017)
- [Super-Acceleration with Cyclical Step-sizes](https://mlsanity.com/paper/2106.09687/) (2021)
- [Exploring loss function topology with cyclical learning rates](https://mlsanity.com/paper/1702.04283/) (2017)
- [Compressed Particle-Based Federated Bayesian Learning and Unlearning](https://mlsanity.com/paper/2209.07267/) (2022)
- [General Cyclical Training of Neural Networks](https://mlsanity.com/paper/2202.08835/) (2022)

## Built on by (most cited first, 6 of 6)

- [A Unified Benchmark of Federated Learning with Kolmogorov-Arnold Networks for Medical Imaging](https://mlsanity.com/paper/2504.19639/) (2025)
- [Debunking Optimization Myths in Federated Learning for Medical Image Classification](https://mlsanity.com/paper/2507.19822/) (2025)
- [Battery-aware Cyclic Scheduling in Energy-harvesting Federated Learning](https://mlsanity.com/paper/2504.12181/) (2025)
- [Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks](https://mlsanity.com/paper/2410.23824/) (2024)
- [Embedding Byzantine Fault Tolerance into Federated Learning via Consistency Scoring](https://mlsanity.com/paper/2411.10212/) (2024)
- [Beyond Fixed Rounds: Data-Free Early Stopping for Practical Federated Learning](https://mlsanity.com/paper/2601.22669/) (2026)

## Abstract (arXiv)

Federated learning (FL) aims at optimizing a shared global model over multiple edge devices without transmitting (private) data to the central server. While it is theoretically well-known that FL yields an optimal model -- centrally trained model assuming availability of all the edge device data at the central server -- under mild condition, in practice, it often requires massive amount of iterations until convergence, especially under presence of statistical/computational heterogeneity. This paper utilizes cyclic learning rate at the server side to reduce the number of training iterations with increased performance without any additional computational costs for both the server and the edge devices. Numerical results validate that, simply plugging-in the proposed cyclic aggregation to the existing FL algorithms effectively reduces the number of training iterations with improved performance.