As the complexity of deep neural networks (DNNs) trend to grow to absorb the
increasing sizes of data, memory and energy consumption has been receiving more
and more attentions for industrial applications, especially on mobile devices.
This paper presents a novel structure based on functional hashing to compress
DNNs, namely FunHashNN. For each entry in a deep net, FunHashNN uses multiple
low-cost hash functions to fetch values in the compression space, and then
employs a small reconstruction network to recover that entry. The
reconstruction network is plugged into the whole network and trained jointly.
FunHashNN includes the recently proposed HashedNets as a degenerated case, and
benefits from larger value capacity and less reconstruction loss. We further
discuss extensions with dual space hashing and multi-hops. On several benchmark
datasets, FunHashNN demonstrates high compression ratios with little loss on
prediction accuracy.

本文提出一种基于功能散列的新型结构 FunHashNN，通过利用多个低成本的散列函数获取压缩空间中的值，再使用小型重建网络恢复每个深层网络中的条目，从而高效地压缩深度神经网络，经实验证明，FunHashNN 在多个基准数据集上表现出较高的压缩比和准确率。