arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.06309cs.LGcs.AI
收藏

时空分裂学习

Spatio-Temporal Split Learning

Korea University(高丽大学);Dankook University(檀国大学)

Joongheon Kim, Seunghoon Park, Soyi Jung, Seehwan Yoo

摘要:

为了实现隐私保护的深度神经网络计算,提出了一种新的具有多个端系统的分裂学习框架.在传统的分离学习框架中,深度神经网络计算被分离到多个计算系统中以隐藏整个网络架构。在我们提出的框架中,多个计算端系统在分裂学习计算中共享一个集中式服务器,其中多个端系统具有输入和第一隐藏层,而集中式服务器具有其他隐藏层和输出层。这种框架被称为时空分裂学习,它在空间上是分离的,用于从多个终端系统收集数据,并且由于分裂学习的性质,在时间上也是分离的。我们的性能评估验证,我们提出的框架显示接近最佳的准确性,同时保护数据隐私。

英文摘要:

This paper proposes a novel split learning framework with multiple end-systems in order to realize privacypreserving deep neural network computation. In conventional split learning frameworks, deep neural network computation is separated into multiple computing systems for hiding entire network architectures. In our proposed framework, multiple computing end-systems are sharing one centralized server in split learning computation, where the multiple end-systems are with input and first hidden layers and the centralized server is with the other hidden layers and output layer. This framework, which is called as spatio-temporal split learning, is spatially separated for gathering data from multiple end-systems and also temporally separated due to the nature of split learning. Our performance evaluation verifies that our proposed framework shows nearoptimal accuracy while preserving data privacy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑