English

Graph-based Neural Acceleration for Nonnegative Matrix Factorization

Machine Learning 2022-02-02 v1 Numerical Analysis Numerical Analysis Optimization and Control Machine Learning

Abstract

We describe a graph-based neural acceleration technique for nonnegative matrix factorization that builds upon a connection between matrices and bipartite graphs that is well-known in certain fields, e.g., sparse linear algebra, but has not yet been exploited to design graph neural networks for matrix computations. We first consider low-rank factorization more broadly and propose a graph representation of the problem suited for graph neural networks. Then, we focus on the task of nonnegative matrix factorization and propose a graph neural network that interleaves bipartite self-attention layers with updates based on the alternating direction method of multipliers. Our empirical evaluation on synthetic and two real-world datasets shows that we attain substantial acceleration, even though we only train in an unsupervised fashion on smaller synthetic instances.

Keywords

Cite

@article{arxiv.2202.00264,
  title  = {Graph-based Neural Acceleration for Nonnegative Matrix Factorization},
  author = {Jens Sjölund and Maria Bånkestad},
  journal= {arXiv preprint arXiv:2202.00264},
  year   = {2022}
}

Comments

Authors contributed equally