Multi-label HD Classification in 3D Flash-猫眼课题宝

DOI：

10.1109/vlsi-soc46417.2020.9344070

发表时间：

2020-10

期刊：

2020 IFIP/IEEE 28th International Conference on Very Large Scale Integration (VLSI-SOC)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Justin Morris;Yilun Hao;Saransh Gupta;R. Ramkumar;Jeffrey Yu;M. Imani;Baris Aksanli;Tajana Simunic

在实践中，许多分类问题将每个样本映射到多个标签-这被称为多标签分类。在这项工作中，我们提出了Multi-label HD，一个使用超维计算（HD）的三维存储多标签分类系统。Multi-label HD是首个支持多标签分类的高清系统。我们提出了两种不同的HD到Multi-label HD的映射。第一个是Power Set HD，它通过为每个标签组合创建一个新类，将多标签问题转化为单标签分类。第二个是Multi-Model HD，它为每个可能的标签创建一个二元分类模型。我们的评估显示，作为最先进的轻量级多标签分类器，Multi-Model HD平均实现了47.8倍的能源效率和47.1倍的执行时间，同时实现了5%的分类精度提高。Power Set HD的精度比Multi-Model HD高13%，但速度慢2倍。我们的3d闪存加速进一步提高了多标签高清训练的能源效率，比在CPU上训练提高了228美元，延迟降低了610美元。

Many classification problems in practice map each sample to more than one label - this is known as multi-label classification. In this work, we present Multi-label HD, an in 3D storage multi-label classification system that uses Hyperdimensional Computing (HD). Multi-label HD is the first HD system to support multi-label classification. We propose two different mappings of HD to Multi-label HD. The first, Power Set HD, transforms the multi-label problem into single-label classification by creating a new class for each label combination. The second, Multi-Model HD, creates a binary classification model for each possible label. Our evaluation shows that Multi-Model HD achieves, on average, $47.8\times$ higher energy efficiency and $47.1\times$ faster execution time while achieving 5% higher classification accuracy as state-of-the-art light-weight multi-label classifiers. Power Set HD achieves 13% higher accuracy than Multi-Model HD, but is $2\times$ slower. Our 3D-flash acceleration further improves the energy efficiency of Multi-label HD training by $228\times$ and reduces the latency by $610\times$ vs training on a CPU.

Multi-label HD Classification in 3D Flash

文献摘要

相似文献