# Efficient and Less Centralized Federated Learning

arXiv: https://arxiv.org/abs/2106.06627 · HTML: https://mlsanity.com/paper/2106.06627/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2021.

## Built on by (most cited first, 8 of 8)

- [On the Convergence of Clustered Federated Learning](https://mlsanity.com/paper/2202.06187/) (2022)
- [Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey](https://mlsanity.com/paper/2302.02573/) (2023)
- [Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beat](https://mlsanity.com/paper/2309.03237/) (2023)
- [CELEST: Federated Learning for Globally Coordinated Threat Detection](https://mlsanity.com/paper/2205.11459/) (2022)
- [Introducing Federated Learning into Internet of Things ecosystems -- preliminary considerations](https://mlsanity.com/paper/2207.07700/) (2022)
- [Failure-tolerant Distributed Learning for Anomaly Detection in Wireless Networks](https://mlsanity.com/paper/2303.13015/) (2023)
- [FedDec: Peer-to-peer Aided Federated Learning](https://mlsanity.com/paper/2306.06715/) (2023)
- [Defining Decentralization: An Ontological Perspective](https://mlsanity.com/paper/2608.09748/) (2026)

## Abstract (arXiv)

With the rapid growth in mobile computing, massive amounts of data and computing resources are now located at the edge. To this end, Federated learning (FL) is becoming a widely adopted distributed machine learning (ML) paradigm, which aims to harness this expanding skewed data locally in order to develop rich and informative models. In centralized FL, a collection of devices collaboratively solve a ML task under the coordination of a central server. However, existing FL frameworks make an over-simplistic assumption about network connectivity and ignore the communication bandwidth of the different links in the network. In this paper, we present and study a novel FL algorithm, in which devices mostly collaborate with other devices in a pairwise manner. Our nonparametric approach is able to exploit network topology to reduce communication bottlenecks. We evaluate our approach on various FL benchmarks and demonstrate that our method achieves 10X better communication efficiency and around 8% increase in accuracy compared to the centralized approach.