paper-with-me

홈 › Papers

Mitigating System Bias in Resource Constrained Asynchronous Federated Learning Systems

2024-01-24 · Jikun Gao, Ioannis Mavromatis, Peizheng Li, Pietro Carnelli, Aftab Khan

Federated learning (FL) systems face performance challenges in dealing with heterogeneous devices and non-identically distributed data across clients. We propose a dynamic global model aggregation method within Asynchronous Federated Learning (AFL) deployments to address these issues. Our aggregation method scores and adjusts the weighting of client model updates based on their upload frequency to accommodate differences in device capabilities. Additionally, we also immediately provide an updated global model to clients after they upload their local models to reduce idle time and improve training efficiency. We evaluate our approach within an AFL deployment consisting of 10 simulated clients with heterogeneous compute constraints and non-IID data. The simulation results, using the FashionMNIST dataset, demonstrate over 10% and 19% improvement in global model accuracy compared to state-of-the-art methods PAPAYA and FedAsync, respectively. Our dynamic aggregation method allows reliable global model training despite limiting client resources and statistical data heterogeneity. This improves robustness and scalability for real-world FL deployments.

📄 PDF Abstract BibTeX arXiv:2401.13366

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML

2025-01-16 · Tehila Dahan, Kfir Y. Levy

We address the challenges of Byzantine-robust training in asynchronous distributed machine learning systems, aiming to enhance efficiency amid massive parallelization and heterogeneous computing resources. Asynchronous s…

FAVANO: Federated AVeraging with Asynchronous NOdes

2023-05-25 · Louis Leconte, Van Minh Nguyen, Eric Moulines

In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO, for training Deep Neural Networks (DNNs) in resource-constrained environments. Despite its popularity, ``classical'' f…

Federated Learning

DriftGuard: Mitigating Asynchronous Data Drift in Federated Learning

2026-03-19 · Yizhou Han, Di Wu, Blesson Varghese arxiv

In real-world Federated Learning (FL) deployments, data distributions on devices that participate in training evolve over time. This leads to asynchronous data drift, where different devices shift at different times and …

Federated LearningContinual Learning

FedCure: Mitigating Participation Bias in Semi-Asynchronous Federated Learning with Non-IID Data

2025-11-13 · Yue Chen, Jianfeng Lu, Shuqing Cao, Wei Wang 외 arxiv

While semi-asynchronous federated learning (SAFL) combines the efficiency of synchronous training with the flexibility of asynchronous updates, it inherently suffers from participation bias, which is further exacerbated …

Computational EfficiencyFederated Learning

Bringing Order to Asynchronous SGD: Towards Optimality under Data-Dependent Delays with Momentum

2026-05-03 · Tehila Dahan, Roie Reshef, Sharon Goldstein, Kfir Y. Levy arxiv

Asynchronous stochastic gradient descent (SGD) enables scalable distributed training but suffers from gradient staleness. Existing mitigation strategies, such as delay-adaptive learning rates and staleness-aware filterin…