# FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling

arXiv: https://arxiv.org/abs/2009.10748 · HTML: https://mlsanity.com/paper/2009.10748/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2020.

## Built on by (most cited first, 27 of 27)

- [Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networks](https://mlsanity.com/paper/2108.09103/) (2021)
- [FedCross: Towards Accurate Federated Learning via Multi-Model Cross-Aggregation](https://mlsanity.com/paper/2210.08285/) (2022)
- [HiFlash: Communication-Efficient Hierarchical Federated Learning with Adaptive Staleness Control and Heterogeneity-aware Client-Edge Association](https://mlsanity.com/paper/2301.06447/) (2023)
- [Exploiting Label Skews in Federated Learning with Model Concatenation](https://mlsanity.com/paper/2312.06290/) (2023)
- [Is Aggregation the Only Choice? Federated Learning via Layer-wise Model Recombination](https://mlsanity.com/paper/2305.10730/) (2023)
- [Compositional federated learning: Applications in distributionally robust averaging and meta learning](https://mlsanity.com/paper/2106.11264/) (2021)
- [Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing](https://mlsanity.com/paper/2103.16031/) (2021)
- [Fast Adaptive Federated Bilevel Optimization](https://mlsanity.com/paper/2211.01122/) (2022)
- [Multi-Model Federated Learning with Provable Guarantees](https://mlsanity.com/paper/2207.04330/) (2022)
- [CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularization](https://mlsanity.com/paper/2302.10413/) (2023)
- [Federated Learning: Issues in Medical Application](https://mlsanity.com/paper/2109.00202/) (2021)
- [FedEntropy: Efficient Device Grouping for Federated Learning Using Maximum Entropy Judgment](https://mlsanity.com/paper/2205.12038/) (2022)
- [Faster Convergence on Heterogeneous Federated Edge Learning: An Adaptive Clustered Data Sharing Approach](https://mlsanity.com/paper/2406.09776/) (2024)
- [Dataset Distillation-based Hybrid Federated Learning on Non-IID Data](https://mlsanity.com/paper/2409.17517/) (2024)
- [Robust Convergence in Federated Learning through Label-wise Clustering](https://mlsanity.com/paper/2112.14244/) (2021)
- [Faster Adaptive Momentum-Based Federated Methods for Distributed Composition Optimization](https://mlsanity.com/paper/2211.01883/) (2022)
- [CaBaFL: Asynchronous Federated Learning via Hierarchical Cache and Feature Balance](https://mlsanity.com/paper/2404.12850/) (2024)
- [FedCAT: Towards Accurate Federated Learning via Device Concatenation](https://mlsanity.com/paper/2202.12751/) (2022)
- [Federated Learning for Commercial Image Sources](https://mlsanity.com/paper/2507.12903/) (2025)
- [FedMR: Fedreated Learning via Model Recombination](https://mlsanity.com/paper/2208.07677/) (2022)
- [RaftFed: A Lightweight Federated Learning Framework for Vehicular Crowd Intelligence](https://mlsanity.com/paper/2310.07268/) (2023)
- [KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting](https://mlsanity.com/paper/2404.12846/) (2024)
- [CDFL: Efficient Federated Human Activity Recognition using Contrastive Learning and Deep Clustering](https://mlsanity.com/paper/2407.12287/) (2024)
- [Secure Generalization through Stochastic Bidirectional Parameter Updates Using Dual-Gradient Mechanism](https://mlsanity.com/paper/2504.02213/) (2025)
- [When To Adapt? Adapting the Model or Data in Federated Medical Imaging](https://mlsanity.com/paper/2605.00892/) (2026)
- [Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration](https://mlsanity.com/paper/2609.07312/) (2026)
- [Protocol Choices Matter More Than the Aggregation Algorithm: Federated Learning for In-Hospital Mortality Prediction in Care-Unit and Multi-Hospital Federations](https://mlsanity.com/paper/2610.17265/) (2026)

## Abstract (arXiv)

We develop FedCluster--a novel federated learning framework with improved optimization efficiency, and investigate its theoretical convergence properties. The FedCluster groups the devices into multiple clusters that perform federated learning cyclically in each learning round. Therefore, each learning round of FedCluster consists of multiple cycles of meta-update that boost the overall convergence. In nonconvex optimization, we show that FedCluster with the devices implementing the local {stochastic gradient descent (SGD)} algorithm achieves a faster convergence rate than the conventional {federated averaging (FedAvg)} algorithm in the presence of device-level data heterogeneity. We conduct experiments on deep learning applications and demonstrate that FedCluster converges significantly faster than the conventional federated learning under diverse levels of device-level data heterogeneity for a variety of local optimizers.