EUVIMEDEUVIMED entdecken
Crossref

Graph Neural Networks and Applied Linear Algebra

Nicholas S. Moore, Eric C. Cyr, Peter Ohm, Christopher M. Siefert, Raymond S. Tuminaro

SIAM Review · 31.03.2025 · 67 (1) · 141-175

DOI: 10.1137/23m1609786 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Review, online erschienen am 06.02.2025. Verfasst von Nicholas S. Moore und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Exascale Computing Project, MMICC, Office of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sparse matrix computations are ubiquitous in scientific computing. Given the recent interest in scientific machine learning, it is natural to ask how sparse matrix computations can leverage neural networks (NNs). Unfortunately, multilayer perceptron (MLP) NNs are typically not natural for either graph or sparse matrix computations. The issue lies with the fact that MLPs require fixed-sized inputs, while scientific applications generally generate sparse matrices with arbitrary dimensions and a wide range of different nonzero patterns (or matrix graph vertex interconnections). While convolutional NNs could possibly address matrix graphs where all vertices have the same number of nearest neighbors, a more general approach is needed for arbitrary sparse matrices, e.g., those arising from discretized partial differential equations on unstructured meshes. Graph neural networks (GNNs) are one such approach suitable to sparse matrices. The key idea is to define aggregation functions (e.g., summations) that operate on variable-size input data to produce data of a fixed output size so that MLPs can be applied. The goal of this paper is to provide an introduction to GNNs for a numerical linear algebra audience. Concrete GNN examples are provided to illustrate how many common linear algebra tasks can be accomplished using GNNs. We focus on iterative and multigrid methods that employ computational kernels such as matrix-vector products, interpolation, relaxation methods, and strength-of-connection measures. Our GNN examples include cases where parameters are determined a priori as well as cases where parameters must be learned. The intent of this paper is to help computational scientists understand how GNNs can be used to adapt machine learning concepts to computational tasks associated with sparse matrices. It is hoped that this understanding will further stimulate data-driven extensions of classical sparse linear algebra tasks.

Förderung

  • Exascale Computing Project
  • MMICC
  • Office of Science

Zitieren

APA

Moore, N. S., Cyr, E. C., Ohm, P., Siefert, C. M., & Tuminaro, R. S. (2025). Graph Neural Networks and Applied Linear Algebra. SIAM Review, 67(1), 141-175. https://doi.org/10.1137/23m1609786

Vancouver

Moore NS, Cyr EC, Ohm P, Siefert CM, Tuminaro RS. Graph Neural Networks and Applied Linear Algebra. SIAM Review. 2025;67(1):141-175. doi:10.1137/23m1609786

BibTeX
@article{Moore2025,
  author = {Moore, Nicholas S. and Cyr, Eric C. and Ohm, Peter and Siefert, Christopher M. and Tuminaro, Raymond S.},
  title = {Graph Neural Networks and Applied Linear Algebra},
  journal = {SIAM Review},
  year = {2025},
  volume = {67},
  number = {1},
  pages = {141--175},
  doi = {10.1137/23m1609786}
}
Kostenlos starten →