AFBS:Buffer Gradient Selection in Semi-asynchronous Federated Learning
Not on the map. Why?
Abstract (arXiv)
Asynchronous federated learning (AFL) accelerates training by eliminating the need to wait for stragglers, but its asynchronous nature introduces gradient staleness, where outdated gradients degrade performance. Existing solutions address this issue with gradient buffers, forming a semi-asynchronous framework. However, this approach struggles when buffers accumulate numerous stale gradients, as blindly aggregating all gradients can harm training. To address this, we propose AFBS (Asynchronous FL Buffer Selection), the first algorithm to perform gradient selection within buffers while ensuring privacy protection. Specifically, the client sends the random projection encrypted label distribution matrix before training, and the server performs client clustering based on it. During training, server scores and selects gradients within each cluster based on their informational value, discarding low-value gradients to enhance semi-asynchronous federated learning. Extensive experiments in highly heterogeneous system and data environments demonstrate AFBS's superior performance compared to state-of-the-art methods. Notably, on the most challenging task, CIFAR-100, AFBS improves accuracy by up to 4.8% over the previous best algorithm and reduces the time to reach target accuracy by 75%.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 26 of its 43 references that are in the map. First posted on arXiv 15 Jun 2025.
Builds on
26 of 43 references.
References · 26
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2020Adaptive Federated Optimizationcited by 1,046
- 2016Bag of Tricks for Efficient Text Classificationcited by 876
- 2021Model-Contrastive Federated Learningcited by 766
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2021Federated Learning Based on Dynamic Regularizationcited by 562
- 2020An Efficient Framework for Clustered Federated Learningcited by 511
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
- 2019Federated Machine Learning: Concept and Applicationscited by 412
14 more
- 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
- 2019Asynchronous Federated Optimizationcited by 267
- 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
- 2020Federated Visual Classification with Real-World Data Distributioncited by 128
- 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 100
- 2019Robust Federated Learning in a Heterogeneous Environmentcited by 90
- 2022Client Selection in Federated Learning: Principles, Challenges, and Opportunitiescited by 62
- 2020Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneitycited by 56
- 2023FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Updatecited by 32
- 2021PFA: Privacy-preserving Federated Adaptation for Effective Model Personalizationcited by 18
- 2014The Johnson-Lindenstrauss lemma is optimal for linear dimensionality reductioncited by 12
- 2023FLGo: A Fully Customizable Federated Learning Platformcited by 12
- 2024FedFa: A Fully Asynchronous Training Paradigm for Federated Learningcited by 12
- 2025Corrected with the Latest Version: Make Robust Asynchronous Federated Learning Possiblecited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.