Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noise

Upadhyay, Antesh; Hashemi, Abolfazl

doi:10.1109/access.2023.3288613

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar phenomena, highlighting significant performance declines in FedAvg [1] under noisy conditions or with non-i.i.d. data, are documented in [22], [26]. Conversely, QHetFed, the learning algorithm proposed in this work, implements a single local step in intra-set iterations, where the gradient is derived from aggregated data rather than local computations, potentially mitigating the impact of noise or deviations.…”

Section: Proposed Hierarchical Schemementioning

confidence: 99%

A Hessian-Based Federated Learning Approach to Tackle Statistical Heterogeneity

Ahmad,

Luo,

Robles-Kelly

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper presents a novel hierarchical federated learning algorithm within multiple sets that incorporates quantization for communication-efficiency and demonstrates resilience to statistical heterogeneity. Unlike conventional hierarchical federated learning algorithms, our approach combines gradient aggregation in intra-set iterations with model aggregation in inter-set iterations. We offer a comprehensive analytical framework to evaluate its optimality gap and convergence rate, comparing these aspects with those of conventional algorithms. Additionally, we develop a problem formulation to derive optimal system parameters in a closed-form solution. Our findings reveal that our algorithm consistently achieves high learning accuracy over a range of parameters and significantly outperforms other hierarchical algorithms, particularly in scenarios with heterogeneous data distributions.

show abstract

Section: Proposed Hierarchical Schemementioning

confidence: 99%