arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.04562cs.CVcs.LG
收藏

用于多任务内存高效推理的深度虚拟网络

Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks

University of Oxford(牛津大学);Seoul National University(首尔国立大学)

Eunwoo Kim, Chanho Ahn, Philip H. S. Torr, Songhwai Oh

摘要:

深度网络本质上会消耗大量内存。一个自然的问题出现了,我们是否可以在保持性能的同时减少内存需求。特别是,在这项工作中,我们解决了多任务的记忆有效学习的问题。为此,我们提出了一种新的网络架构,产生多个不同配置的网络,称为深度虚拟网络(DVNs),用于不同的任务。每个DVN专门用于单个任务,并分层结构。分层结构包含对应于不同数量的参数的多个层级,使得能够针对不同的存储器预算进行多个推断。深度虚拟网络的构建块基于网络的不相交参数集合,我们称之为单元。深度虚拟网络中的最低层级是单元,并且较高层级包含较低层级的单元和其他附加单元。给定参数数量的预算,可以选择不同级别的深度虚拟网络来执行任务。一个单元可以由不同的DVN共享,允许在一个网络中有多个DVN。此外,共享单元为目标任务提供从另一个任务学到的额外知识。DVN的这种协作配置使得可以以存储器感知的方式处理不同的任务。我们的实验表明,所提出的方法优于现有的方法,多个任务。值得注意的是,我们比其他人更有效,因为它允许对所有任务进行记忆感知推理。

英文摘要:

Deep networks consume a large amount of memory by their nature. A natural question arises can we reduce that memory requirement whilst maintaining performance. In particular, in this work we address the problem of memory efficient learning for multiple tasks. To this end, we propose a novel network architecture producing multiple networks of different configurations, termed deep virtual networks (DVNs), for different tasks. Each DVN is specialized for a single task and structured hierarchically. The hierarchical structure, which contains multiple levels of hierarchy corresponding to different numbers of parameters, enables multiple inference for different memory budgets. The building block of a deep virtual network is based on a disjoint collection of parameters of a network, which we call a unit. The lowest level of hierarchy in a deep virtual network is a unit, and higher levels of hierarchy contain lower levels' units and other additional units. Given a budget on the number of parameters, a different level of a deep virtual network can be chosen to perform the task. A unit can be shared by different DVNs, allowing multiple DVNs in a single network. In addition, shared units provide assistance to the target task with additional knowledge learned from another tasks. This cooperative configuration of DVNs makes it possible to handle different tasks in a memory-aware manner. Our experiments show that the proposed method outperforms existing approaches for multiple tasks. Notably, ours is more efficient than others as it allows memory-aware inference for all tasks.

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。

↑