@inproceedings{251d405606b742878b3ea4174c99389f,
title = "Reducing the Training Overhead of the HPC Compression Autoencoder via Dataset Proportioning",
abstract = "As the storage overhead of high-performance computing (HPC) data reaches into the petabyte or even exabyte scale, it could be useful to find new methods of compressing such data. The compression autoencoder (CAE) has recently been proposed to compress HPC data with a very high compression ratio. However, this machine learning-based method suffers from the major drawback of lengthy training time. In this paper, we attempt to mitigate this problem by proposing a proportioning scheme to reduce the amount of data that is used for training relative to the amount of data to be compressed. We show that this method drastically reduces the training time without, in most cases, significantly increasing the error. We further explain how this scheme can even improve the accuracy of the CAE on certain datasets. Finally, we provide some guidance on how to determine a suitable proportion of the training dataset to use in order to train the CAE for a given dataset.",
keywords = "Data compression, HPC, autoencoder, machine learning, training time",
author = "Tong Liu and Shakeel Alibhai and Jinzhen Wang and Qing Liu and Xubin He",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 15th IEEE International Conference on Networking, Architecture and Storage, NAS 2021 ; Conference date: 24-10-2021 Through 26-10-2021",
year = "2021",
doi = "10.1109/NAS51552.2021.9605407",
language = "English (US)",
series = "2021 IEEE International Conference on Networking, Architecture and Storage, NAS 2021 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2021 IEEE International Conference on Networking, Architecture and Storage, NAS 2021 - Proceedings",
address = "United States",
}