In the era of big data, efficiently processing and retrieving insights from unstructured data presents a critical challenge. this paper introduces a scalable leader-worker distributed data pipeline designed to handle ...
详细信息
As the number of IoT devices and the volume of data increase, distributedcomputingsystems have become the primary deployment solution for large-scale Internet of things (IoT) environments. Federated Learning (FL) is...
详细信息
ISBN:
(纸本)9783031751097;9783031751103
As the number of IoT devices and the volume of data increase, distributedcomputingsystems have become the primary deployment solution for large-scale Internet of things (IoT) environments. Federated Learning (FL) is a collaborative machine learning framework that allows for model training using data from all participants while protecting their privacy. However, traditional FL suffers from low computational and communication efficiency in large-scale hierarchical cloud-edge collaborative IoT systems. Additionally, due to heterogeneity issues, not all IoT devices necessarily benefit from the global model of traditional FL, but instead require the maintenance of personalized levels in the global training process. therefore we extend FL into a horizontal peer-to-peer (P2P) structure and introduce our P2PFL framework: Efficient Peer-to-peer Federated Learning for Users (EPFLU). EPFLU transitions the paradigms from vertical FL to horizontal P2P structure from the user perspective and incorporates personalized enhancement techniques using private information. through horizontal consensus information aggregation and private information supplementation, EPFLU solves the weakness of traditional FL that dilutes the characteristics of individual client data and leads to model deviation. this structural transformation also significantly alleviates the original communication issues. Additionally, EPFLU has a customized simulation evaluation framework to make it more suitable for real-world large-scale IoT. Within this framework, we design extreme data distribution scenarios and conduct detailed experiments of EPFLU and selected baselines on the MNIST and CIFAR-10 datasets. the results demonstrate that the robust and adaptive EPFLU framework can consistently converge to optimal performance even under extreme data distribution scenarios. Compared withthe selected vertical aggregation and horizontal transmission cumulative aggregation methods, EPFLU achieves communication improve
Photonic integrated circuits provide compact and efficient solutions for multimodal spectroscopic sensors. However, the resulting sensory data is highly complex and contains significant redundancy. To circumvent high ...
详细信息
Brain stroke affects a large number of the population and is one of the primary causes of death and permanent disability, therefore the identification of risk factors is paramount for timely prevention. these interact...
详细信息
暂无评论