# Graph-Assisted Communication-Efficient Ensemble Federated Learning

arXiv: https://arxiv.org/abs/2202.13447 · HTML: https://mlsanity.com/paper/2202.13447/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 27 Feb 2022.

## Builds on (most cited first, 6 of 6)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [FetchSGD: Communication-Efficient Federated Learning with Sketching](https://mlsanity.com/paper/2007.07682/) (2020)
- [Hierarchical Federated Learning Across Heterogeneous Cellular Networks](https://mlsanity.com/paper/1909.02362/) (2019)
- [Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback](https://mlsanity.com/paper/1409.8428/) (2014)
- [Fed-EINI: An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learning](https://mlsanity.com/paper/2105.09540/) (2021)

## Built on by (most cited first, 2 of 2)

- [Personalized Online Federated Learning with Multiple Kernels](https://mlsanity.com/paper/2311.05108/) (2023)
- [Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning](https://mlsanity.com/paper/2410.21547/) (2024)

## Abstract (arXiv)

Communication efficiency arises as a necessity in federated learning due to limited communication bandwidth. To this end, the present paper develops an algorithmic framework where an ensemble of pre-trained models is learned. At each learning round, the server selects a subset of pre-trained models to construct the ensemble model based on the structure of a graph, which characterizes the server's confidence in the models. Then only the selected models are transmitted to the clients, such that certain budget constraints are not violated. Upon receiving updates from the clients, the server refines the structure of the graph accordingly. The proposed algorithm is proved to enjoy sub-linear regret bound. Experiments on real datasets demonstrate the effectiveness of our novel approach.