mlsanityData to 7 Oct 2026

Graph-based Neural Acceleration for Nonnegative Matrix Factorization

arXiv 2202.00264 ↗First posted 1 Feb 2022cs.LG cs.NA math.NAcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 35 of its 64 references that are in the map. First posted on arXiv 1 Feb 2022.

Builds on

35 of 64 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016Layer Normalizationcited by 5,579
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  9. 2020Reformer: The Efficient Transformercited by 1,658
  10. 2018Self-Attention with Relative Position Representationscited by 1,112
  11. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  12. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
23 more
  1. 2016Learning to learn by gradient descent by gradient descentcited by 616
  2. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
  3. 2019Differentiable Convex Optimization Layerscited by 458
  4. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  5. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 313
  6. 2021Combinatorial optimization and reasoning with graph neural networkscited by 267
  7. 2021Learning to Optimize: A Primer and A Benchmarkcited by 206
  8. 2016Learning to Optimizecited by 195
  9. 2020Solving Mixed Integer Programs Using Neural Networkscited by 178
  10. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  11. 2021Generative Adversarial Transformerscited by 120
  12. 2017Geometric Matrix Completion with Recurrent Multi-Graph Neural Networkscited by 88
  13. 2017Neural Optimizer Search with Reinforcement Learningcited by 82
  14. 2014Generalized Low Rank Modelscited by 55
  15. 2018Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applicationscited by 55
  16. 2017Unrolled Optimization with Deep Priorscited by 40
  17. 2017Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Surveycited by 33
  18. 2015A Flexible and Efficient Algorithmic Framework for Constrained Matrix and Tensor Factorizationcited by 30
  19. 2020Reverse engineering learned optimizers reveals known and novel mechanismscited by 19
  20. 2018NIMFA: A Python Library for Nonnegative Matrix Factorizationcited by 10
  21. 2021Neural Fixed-Point Acceleration for Convex Optimizationcited by 10
  22. 2014Algorithms, Initializations, and Convergence for the Nonnegative Matrix Factorizationcited by 9
  23. 2018Data-driven nonsmooth optimizationcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 2.

9 papers.

  1. 2023Learning to Warm-Start Fixed-Point Optimization Algorithmscited by 32
  2. 2023Neural incomplete factorization: learning preconditioners for the conjugate gradient methodcited by 18
  3. 2024Learning incomplete factorization preconditioners for GMREScited by 9
  4. 2024Data-Driven Performance Guarantees for Classical and Learned Optimizerscited by 5
  5. 2025Learning to accelerate distributed ADMM using graph neural networkscited by 3
  6. 2023Archetypal Analysis++: Rethinking the Initialization Strategycited by 2
  7. 2024WARP-LCA: Efficient Convolutional Sparse Coding with Locally Competitive Algorithmcited by 2
  8. 2025Warm-starting active-set solvers using graph neural networkscited by 2
  9. 2022A quantum learning approach based on Hidden Markov Models for failure scenarios generationcited by 0