arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.00599cs.ITmath.IT
收藏

基于注意力的深度神经网络布局交付阵列设计

Placement Delivery Array Design via Attention-Based Deep Neural Network

Zhengming Zhang, Meng Hua, Chunguo Li, Yongming Huang, Luxi Yang

摘要:

Maddah-Ali和Niesen提出了一种分散的编码缓存方案,并已被证明可以减轻网络负载。最近,放置交付阵列(PDA)被提出来表征编码缓存方案。在本文中,首先提出了一个神经结构来学习PDA的建设。该模型利用神经注意机制和强化学习解决了PDA大小可变的问题。它不同于以往的尝试,它不是使用组合优化算法来获得PDA,而是使用序列到序列模型来学习构造PDA。数值结果表明,该方法可以有效地实现编码缓存。我们还表明,我们的方法来构建PDA的复杂性是低的。

英文摘要:

A decentralized coded caching scheme has been proposed by Maddah-Ali and Niesen, and has been shown to alleviate the load of networks. Recently, placement delivery array (PDA) was proposed to characterize the coded caching scheme. In this paper, a neural architecture is first proposed to learn the construction of PDAs. Our model solves the problem of variable size PDAs using mechanism of neural attention and reinforcement learning. It differs from the previous attempts in that, instead of using combined optimization algorithms to get PDAs, it uses sequence-to-sequence model to learn construct PDAs. Numerical results are given to demonstrate that the proposed method can effectively implement coded caching. We also show that the complexity of our method to construct PDAs is low.

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。

↑