arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.06404cs.LGstat.ML
收藏

基于贝叶斯HyperNetworks的快速条件网络压缩

Fast Conditional Network Compression Using Bayesian HyperNetworks

Deakin University(迪肯大学);A2I2(应用人工智能研究所)

Phuoc Nguyen, Truyen Tran, Ky Le, Sunil Gupta, Santu Rana, Dang Nguyen, Trong Nguyen, Shannon Ryan, Svetha Venkatesh

摘要:

我们引入了一个条件压缩问题,并提出了一个快速的框架来解决这个问题,问题是如何在给定目标上下文的情况下,快速地将一个预先训练好的大型神经网络压缩成最优的较小网络,例如只涉及类的子集的上下文或只有有限计算资源可用的上下文。为了解决这个问题,我们提出了一个高效的贝叶斯框架,将给定的大型网络压缩成更小的尺寸,以满足每个上下文要求。我们采用一个超网络参数化的后验分布的权重给定的条件输入和最小化这个贝叶斯神经网络的变分目标。为了进一步减小网络的规模,我们提出了一种新的输入输出组稀疏因子分解的权重,以鼓励更稀疏的生成的权重。我们的方法可以快速生成压缩网络,其大小明显小于基线方法。

英文摘要:

We introduce a conditional compression problem and propose a fast framework for tackling it. The problem is how to quickly compress a pretrained large neural network into optimal smaller networks given target contexts, e.g. a context involving only a subset of classes or a context where only limited compute resource is available. To solve this, we propose an efficient Bayesian framework to compress a given large network into much smaller size tailored to meet each contextual requirement. We employ a hypernetwork to parameterize the posterior distribution of weights given conditional inputs and minimize a variational objective of this Bayesian neural network. To further reduce the network sizes, we propose a new input-output group sparsity factorization of weights to encourage more sparseness in the generated weights. Our methods can quickly generate compressed networks with significantly smaller sizes than baseline methods.

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。

↑