# AFBS:Buffer Gradient Selection in Semi-asynchronous Federated Learning

arXiv: https://arxiv.org/abs/2506.12754 · HTML: https://mlsanity.com/paper/2506.12754/

## 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 (most cited first, 26 of 26)

- [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)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://mlsanity.com/paper/1910.01991/) (2019)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [Asynchronous Federated Optimization](https://mlsanity.com/paper/1903.03934/) (2019)
- [Federated Learning with Buffered Asynchronous Aggregation](https://mlsanity.com/paper/2106.06639/) (2021)
- [Federated Visual Classification with Real-World Data Distribution](https://mlsanity.com/paper/2003.08082/) (2020)
- [Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation](https://mlsanity.com/paper/1903.07424/) (2019)
- [Robust Federated Learning in a Heterogeneous Environment](https://mlsanity.com/paper/1906.06629/) (2019)
- [Client Selection in Federated Learning: Principles, Challenges, and Opportunities](https://mlsanity.com/paper/2211.01549/) (2022)
- [Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity](https://mlsanity.com/paper/2012.14453/) (2020)
- [FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Update](https://mlsanity.com/paper/2312.05770/) (2023)
- [PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization](https://mlsanity.com/paper/2103.01548/) (2021)
- [The Johnson-Lindenstrauss lemma is optimal for linear dimensionality reduction](https://mlsanity.com/paper/1411.2404/) (2014)
- [FLGo: A Fully Customizable Federated Learning Platform](https://mlsanity.com/paper/2306.12079/) (2023)
- [FedFa: A Fully Asynchronous Training Paradigm for Federated Learning](https://mlsanity.com/paper/2404.11015/) (2024)
- [Corrected with the Latest Version: Make Robust Asynchronous Federated Learning Possible](https://mlsanity.com/paper/2504.04081/) (2025)

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

- [FedPSA: Modeling Behavioral Staleness in Asynchronous Federated Learning](https://mlsanity.com/paper/2602.15337/) (2026)
- [FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning](https://mlsanity.com/paper/2609.07192/) (2026)

## 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%.