MSA-Fed: Model Similarity Aware Federated Learning for Data Heterogeneous QoS Prediction

Liu, Y.H.; Xu, Zhuo; Jian, Lin; Cai, Lingru

doi:10.1109/cscloud-edgecom58631.2023.00055

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They fist employ tensors to encode QoS data in multidimensional forms and establish a unique model for individual edge servers. And Liu et al [29]introduced a method to effectively use the similarity between models for model training and prediction under the federated model framework. Considering heterogeneous local QoS datasets, Xu et al [30] proposed a federated learning framework which divides the client into multiple regions for model aggregation and reduces the time of model convergence.…”

Section: Related Workmentioning

confidence: 99%

LCSA-Fed: A low cost semi-asynchronous federated learning based on lag tolerance for services QoS prediction

Cai,

Liu,

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

As a distributed training method, federated learning (FL) has been widely used in the field of quality-of-service (QoS) prediction. However, existing FL-based QoS prediction methods ignore the unreliability of end devices, which will lead to wasted training resources and high communication costs. Considering that the instability of end devices in real training environments, we propose a low cost semi-asynchronous federated learning method (LCSA-Fed) based on lag tolerance to overcome the lower convergence rate and suboptimal prediction accuracy of models. LCSA-Fed is able to reduce model communication costs and training costs by tolerating relatively lagging local models. At the same time, we employ innovations in both the user selection phase and the model aggregation phase to improve prediction accuracy while reducing overheads. By conducting relevant validation experiments on a publicly available QoS dataset, we conclude that our model LCSA-Fed can effectively reduce overhead and improve prediction accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%