Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation
Not on the map. Why?
Abstract (arXiv)
Decentralized Federated Learning(DFL) enables collaborative model training across wireless edge nodes, including IoT deployments, autonomous vehicles, UAV swarms, and satellite constellations. Operating over lossy wireless links under constraints, these systems cannot rely on retransmissions, so model parameters must be accepted as partial chunks, leading to two key failure modes, which are selection bias, where poor-quality links are systematically under-represented in gossip aggregation, and update staleness, where asynchronous nodes contribute outdated models. We prove that classical gossip aggregation introduces irreducible selection bias proportional to the link-loss rate. We propose DFL-AA (Decentralized Federated Learning with Adaptive AoI-weighted Aggregation), which corrects selection bias using Inverse Probability Weighting (IPW) with online channel estimation and mitigates staleness via Age-of-Information (AoI) decay without requiring a global clock. We prove that DFL-AA removes link-quality distortion in expectation and consistently outperforms state-of-the-art baselines across varying loss rates and heterogeneous channel conditions on fixed directed topologies.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 50 references that are in the map. First posted on arXiv 9 Jun 2026.
Builds on
26 of 50 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2019Towards Federated Learning at Scale: System Designcited by 832
- 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
- 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
- 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
- 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
- 2017Asynchronous Decentralized Parallel Stochastic Gradient Descentcited by 159
- 2018Stochastic Gradient Push for Distributed Deep Learningcited by 152
- 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
- 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
14 more
- 2021Federated Learning: Opportunities and Challengescited by 84
- 2020Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applicationscited by 62
- 2023FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Updatecited by 32
- 2020Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmissioncited by 23
- 2022SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communicationcited by 21
- 2022Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networkingcited by 18
- 2023AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devicescited by 15
- 2022Adaptive Configuration for Heterogeneous Participants in Decentralized Federated Learningcited by 11
- 2022MOB-FL: Mobility-Aware Federated Learning for Intelligent Connected Vehiclescited by 8
- 2025Mobility-Aware Decentralized Federated Learning with Joint Optimization of Local Iteration and Leader Selection for Vehicular Networkscited by 5
- 2024pFedGame -- Decentralized Federated Learning using Game Theory in Dynamic Topologycited by 2
- 2024ProFe: Communication-Efficient Decentralized Federated Learning via Distillation and Prototypescited by 2
- 2025Mobility-Aware Multi-Task Decentralized Federated Learning for Vehicular Networks: Modeling, Analysis, and Optimizationcited by 1
- 2026Centralized vs Decentralized Federated Learning: A trade-off performance analysiscited by 1
Built on by
Not cited yet.