@inproceedings{498e0ab63f4f4fd9b0f78bf79b6d2ba4,
title = "Exploring Transfer Learning to Reduce Training Overhead of HPC Data in Machine Learning",
abstract = "Nowadays, scientific simulations on high-performance computing (HPC) systems can generate large amounts of data (in the scale of terabytes or petabytes) per run. When this huge amount of HPC data is processed by machine learning applications, the training overhead will be significant. Typically, the training process for a neural network can take several hours to complete, if not longer. When machine learning is applied to HPC scientific data, the training time can take several days or even weeks. Transfer learning, an optimization usually used to save training time or achieve better performance, has potential for reducing this large training overhead. In this paper, we apply transfer learning to a machine learning HPC application. We find that transfer learning can reduce training time without, in most cases, significantly increasing the error. This indicates transfer learning can be very useful for working with HPC datasets in machine learning applications.",
keywords = "HPC data, machine learning, transfer learning",
author = "Tong Liu and Shakeel Alibhai and Jinzhen Wang and Qing Liu and Xubin He and Chentao Wu",
year = "2019",
month = aug,
doi = "10.1109/NAS.2019.8834723",
language = "English (US)",
series = "2019 IEEE International Conference on Networking, Architecture and Storage, NAS 2019 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Conference on Networking, Architecture and Storage, NAS 2019 - Proceedings",
address = "United States",
note = "14th IEEE International Conference on Networking, Architecture and Storage, NAS 2019 ; Conference date: 15-08-2019 Through 17-08-2019",
}