BriefGPT.xyz
May, 2024
非联邦多任务分割学习的异构源
Non-Federated Multi-Task Split Learning for Heterogeneous Sources
HTML
PDF
Yilin Zheng, Atilla Eryilmaz
TL;DR
边缘网络和移动计算的发展需要设计新的分布式机器学习机制来服务于异构数据源。本文提出了一种多任务分割学习(MTSL)框架,结合了分割学习(SL)的优点和分布式网络架构的灵活性,以实现高效处理异构数据源的多任务学习,具有快速收敛、低通信成本和对异质数据的鲁棒性等优势。
Abstract
With the development of
edge networks
and mobile computing, the need to serve
heterogeneous data sources
at the network edge requires the design of new
→