# Accelerating Asynchronous Federated Learning Convergence via Opportunistic Mobile Relaying

arXiv: https://arxiv.org/abs/2206.04742 · HTML: https://mlsanity.com/paper/2206.04742/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 29 of 29)

- [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)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge](https://mlsanity.com/paper/1804.08333/) (2018)
- [Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning](https://mlsanity.com/paper/1807.06629/) (2018)
- [Tighter Theory for Local SGD on Identical and Heterogeneous Data](https://mlsanity.com/paper/1909.04746/) (2019)
- [Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning](https://mlsanity.com/paper/2101.11203/) (2021)
- [Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations](https://mlsanity.com/paper/1906.02367/) (2019)
- [Revisiting Distributed Synchronous SGD](https://mlsanity.com/paper/1702.05800/) (2017)
- [SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum](https://mlsanity.com/paper/1910.00643/) (2019)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [Asynchronous Stochastic Gradient Descent with Delay Compensation](https://mlsanity.com/paper/1609.08326/) (2016)
- [LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning](https://mlsanity.com/paper/1805.09965/) (2018)
- [Peer-to-peer Federated Learning on Graphs](https://mlsanity.com/paper/1901.11173/) (2019)
- [Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach](https://mlsanity.com/paper/2003.08725/) (2020)
- [Accelerating Federated Learning via Momentum Gradient Descent](https://mlsanity.com/paper/1910.03197/) (2019)
- [FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers](https://mlsanity.com/paper/2010.05958/) (2020)
- [Wireless Communications for Collaborative Federated Learning](https://mlsanity.com/paper/2006.02499/) (2020)
- [Decentralized Federated Learning via SGD over Wireless D2D Networks](https://mlsanity.com/paper/2002.12507/) (2020)
- [Asynchrony begets Momentum, with an Application to Deep Learning](https://mlsanity.com/paper/1605.09774/) (2016)
- [Toward Understanding the Impact of Staleness in Distributed Machine Learning](https://mlsanity.com/paper/1810.03264/) (2018)
- [Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise](https://mlsanity.com/paper/2007.09208/) (2020)
- [Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization](https://mlsanity.com/paper/2202.01971/) (2022)
- [Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients](https://mlsanity.com/paper/2102.06329/) (2021)
- [A Survey on Device-to-Device Communication in Cellular Networks](https://mlsanity.com/paper/1310.0720/) (2013)
- [Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUs](https://mlsanity.com/paper/1606.04487/) (2016)

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

- [Decentralized Federated Learning: A Survey and Perspective](https://mlsanity.com/paper/2306.01603/) (2023)
- [Prioritizing Modalities: Flexible Importance Scheduling in Federated Multimodal Learning](https://mlsanity.com/paper/2408.06549/) (2024)
- [Joint Client Assignment and UAV Route Planning for Indirect-Communication Federated Learning](https://mlsanity.com/paper/2304.10744/) (2023)
- [Distribution-Aware Mobility-Assisted Decentralized Federated Learning](https://mlsanity.com/paper/2505.18866/) (2025)
- [Analysis of Asynchronous Federated Learning: Unraveling the Interactions between Gradient Compression, Delay, and Data Heterogeneity](https://mlsanity.com/paper/2504.19903/) (2025)
- [Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification](https://mlsanity.com/paper/2506.07328/) (2025)

## Abstract (arXiv)

This paper presents a study on asynchronous Federated Learning (FL) in a mobile network setting. The majority of FL algorithms assume that communication between clients and the server is always available, however, this is not the case in many real-world systems. To address this issue, the paper explores the impact of mobility on the convergence performance of asynchronous FL. By exploiting mobility, the study shows that clients can indirectly communicate with the server through another client serving as a relay, creating additional communication opportunities. This enables clients to upload local model updates sooner or receive fresher global models. We propose a new FL algorithm, called FedMobile, that incorporates opportunistic relaying and addresses key questions such as when and how to relay. We prove that FedMobile achieves a convergence rate O(frac1√NT), where N is the number of clients and T is the number of communication slots, and show that the optimal design involves an interesting trade-off on the best timing of relaying. The paper also presents an extension that considers data manipulation before relaying to reduce the cost and enhance privacy. Experiment results on a synthetic dataset and two real-world datasets verify our theoretical findings.