Distributed Collaborative Machine Learning (DCML) has emerged in artificial intelligence-empowered edge computing environments, such as the Industrial Internet of Things (IIoT), to process tremendous data generated by...
详细信息
Distributed Collaborative Machine Learning (DCML) has emerged in artificial intelligence-empowered edge computing environments, such as the Industrial Internet of Things (IIoT), to process tremendous data generated by smart devices. However, parallel DCML frameworks require resource-constrained devices to update the entire Deep Neural Network (DNN) models and are vulnerable to reconstruction attacks. Concurrently, the serial DCML frameworks suffer from training efficiency problems due to their serial training nature. In this paper, we propose a Model Pruning-enabled Federated Split Learning framework (MP-FSL) to reduce resource consumption with a secure and efficient training scheme. Specifically, MP-FSL compresses DNN models by adaptive channel pruning and splits each compressed model into two parts that are assigned to the client and the server. Meanwhile, MP-FSL adopts a novel aggregation algorithm to aggregate the pruned heterogeneous models. We implement MP-FSL with a real FL platform to evaluate its performance. The experimental results show that MP-FSL outperforms the state-of-the-art frameworks in model accuracy by up to 1.35%, while concurrently reducing storage and computational resource consumption by up to 32.2% and 26.73%, respectively. These results demonstrate that MP-FSL is a comprehensive solution to the challenges faced by DCML, with superior performance in both reduced resource consumption and enhanced model performance.
This volume constitutes the refereed proceedings of the Confederated International Conferences: Cooperative Information systems, CoopIS 2014, and Ontologies, Databases, and Applications of Semantics, ODBASE 2014, held...
详细信息
ISBN:
(数字)9783662455630
ISBN:
(纸本)9783662455623
This volume constitutes the refereed proceedings of the Confederated International Conferences: Cooperative Information systems, CoopIS 2014, and Ontologies, Databases, and Applications of Semantics, ODBASE 2014, held as part of OTM 2014 in October 2014 in Amantea, Italy.
The 39 full papers presented together with 12 short papers and 5 keynotes were carefully reviewed and selected from a total of 115 submissions. The OTM program covers subjects as follows: process designing and modeling, process enactment, monitoring and quality assessment, managing similarity, software services, improving alignment, collaboration systems and applications, ontology querying methodologies and paradigms, ontology support for web, XML, and RDF data processing and retrieval, knowledge bases querying and retrieval, social network and collaborative methodologies, ontology-assisted event and stream processing, ontology-assisted warehousing approaches, ontology-based data representation, and management in emerging domains.
暂无评论