Journal
2022 IEEE 18TH INTERNATIONAL CONFERENCE ON E-SCIENCE (ESCIENCE 2022)
Volume -, Issue -, Pages 389-390Publisher
IEEE
DOI: 10.1109/eScience55777.2022.00052
Keywords
NSGA-Net; neural architecture search; NAS
Funding
- National Science Foundation (NSF) [1741057, 1740990, 1741040, 1841758, 2223704]
- Joint Directed Research Development (JDRD) program at UTK
- IBM through a Shared University Research Award
- Oak Ridge Leadership Computing Facility [CSC427]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1841758, 1741057] Funding Source: National Science Foundation
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1741040, 1740990] Funding Source: National Science Foundation
Ask authors/readers for more resources
Neural networks are crucial for successful management of high-throughput scientific workflows. This study utilizes a multi-objective neural architecture search approach to generate accurate neural networks while optimizing for computational efficiency. By selecting and refining a subset of networks, efficient networks suitable for data analysis are obtained.
Neural networks (NNs) are increasingly utilized in high-throughput scientific workflows. In this context, NN efficiency is essential for successful workflow management. We use a multi-objective Neural Architecture Search (NAS), NSGA-Net, to search for highly accurate NNs while optimizing for efficient use of computational resources by minimizing FLoating-point Operations Per Second (FLOPS). We define a domain-agnostic methodology to generate NNs with the support of NSGA-Net, select promising NNs that balance accuracy and FLOPS usage, and refine a subset of NNs in order to curate networks suitable for efficient data analysis. We apply this methodology to a protein diffraction use case. Preliminary results show NNs that efficiently classify conformation of proteins with a final accuracy of 97.7% or higher and using only 187 FLOPS.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available