Graph Neural Networks and Applied Linear Algebra v.1.0

RESOURCE

Abstract

SAND2024-01365O The Graph Neural Networks and Applied Linear Algebra is companion software for the educational article with the same title. The software provides illustrative examples of graph neural networks in Matlab and Python. These stand-alone algorithms are for educational purposes. The software also includes graph neural network-based algorithms for a trainable Jacobi iteration as well as diffusion coefficient estimation. The software provides human-interpretable implementations of Graph Neural Networks in Matlab and Python. These implementations are not optimized for performance and instead emphasize readability. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
Developers:
Tuminaro, Raymond [1][2][3] Siefert, Christopher [1][2][3] Ohm, Peter [1][2][3] Moore, Nicholas [1][2][3]
  1. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  3. Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
Release Date:
2023-10-03
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Programming Languages:
MATLAB
Python
Version:
1.0
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
125157
Site Accession Number:
SCR #2960.0
Research Org.:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Country of Origin:
United States
Keywords:
SciDAC

RESOURCE

Citation Formats

Tuminaro, Raymond, Siefert, Christopher, Ohm, Peter, and Moore, Nicholas. Graph Neural Networks and Applied Linear Algebra v.1.0. Computer Software. https://github.com/sandialabs/gnn-applied-linear-algebra. USDOE. 03 Oct. 2023. Web. doi:10.11578/dc.20240319.3.
Tuminaro, Raymond, Siefert, Christopher, Ohm, Peter, & Moore, Nicholas. (2023, October 03). Graph Neural Networks and Applied Linear Algebra v.1.0. [Computer software]. https://github.com/sandialabs/gnn-applied-linear-algebra. https://doi.org/10.11578/dc.20240319.3.
Tuminaro, Raymond, Siefert, Christopher, Ohm, Peter, and Moore, Nicholas. "Graph Neural Networks and Applied Linear Algebra v.1.0." Computer software. October 03, 2023. https://github.com/sandialabs/gnn-applied-linear-algebra. https://doi.org/10.11578/dc.20240319.3.
@misc{ doecode_125157,
title = {Graph Neural Networks and Applied Linear Algebra v.1.0},
author = {Tuminaro, Raymond and Siefert, Christopher and Ohm, Peter and Moore, Nicholas},
abstractNote = {SAND2024-01365O The Graph Neural Networks and Applied Linear Algebra is companion software for the educational article with the same title. The software provides illustrative examples of graph neural networks in Matlab and Python. These stand-alone algorithms are for educational purposes. The software also includes graph neural network-based algorithms for a trainable Jacobi iteration as well as diffusion coefficient estimation. The software provides human-interpretable implementations of Graph Neural Networks in Matlab and Python. These implementations are not optimized for performance and instead emphasize readability. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.},
doi = {10.11578/dc.20240319.3},
url = {https://doi.org/10.11578/dc.20240319.3},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20240319.3}},
year = {2023},
month = {oct}
}