Fetching the paper…
Reading the bibliography…
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.
Some properties of line digraphs
Harary, F. and Norman, R. Z · 1960
Earlier work this paper cites.
Applications of graph theory in linear algebra
Doob, M · 1984
Earlier work this paper cites.
Eigenfaces vs. fisherfaces: Recognition using class specific linear projection
Belhumeur, P. N., Hespanha, J. P., and Kriegman, D. J · 1997
Earlier work this paper cites.
Learning the parts of objects by non-negative matrix factorization
Lee, D. D. and Seung, H. S · 1999
Earlier work this paper cites.
Algorithms for non-negative matrix factorization
Lee, D. D. and Seung, H. S · 2001
Earlier work this paper cites.
Principal component analysis for hyperspectral image classification
Rodarmel, C. and Shan, J · 2002
Earlier work this paper cites.
Algorithms, initializations, and convergence for the nonnegative matrix factorization
Albright, R., Cox, J., Duling, D., Langville, A. N., and Meyer, C · 2006
Earlier work this paper cites.
Document clustering using nonnegative matrix factorization
Shahnaz, F., Berry, M. W., Pauca, V. P., and Plemmons, R. J · 2006
Earlier work this paper cites.
Sparse non-negative matrix factorizations via alternating non-negativity-constrained least squares for microarray data analysis
Kim, H. and Park, H · 2007
Earlier work this paper cites.
Projected gradient methods for nonnegative matrix factorization
Lin, C.-J · 2007
Earlier work this paper cites.
SVD based initialization: A head start for nonnegative matrix factorization
Boutsidis, C. and Gallopoulos, E · 2008
Earlier work this paper cites.
A combinatorial approach to matrix theory and its applications
Brualdi, R. A. and Cvetkovic, D · 2008
Earlier work this paper cites.
Nonnegative matrix factorization based on alternating nonnegativity constrained least squares and active set method
Kim, H. and Park, H · 2008
Earlier work this paper cites.
Learning fast approximations of sparse coding
Gregor, K. and LeCun, Y · 2010
Earlier work this paper cites.
On the complexity of nonnegative matrix factorization
Vavasis, S. A · 2010
Earlier work this paper cites.
Distributed optimization and statistical learning via the alternating direction method of multipliers
Boyd, S., Parikh, N., Chu, E., Peleato, B., and Eckstein, J · 2011
Earlier work this paper cites.
Graph algorithms in the language of linear algebra
Kepner, J. and Gilbert, J · 2011
Earlier work this paper cites.
Generic methods for optimization-based modeling
Domke, J · 2012
Earlier work this paper cites.
Factoring nonnegative matrices with linear programs
Recht, B., Re, C., Tropp, J., and Bittorf, V · 2012
Earlier work this paper cites.
NIMFA: A Python library for nonnegative matrix factorization
Žitnik, M. and Zupan, B · 2012
Earlier work this paper cites.
Fast and robust recursive algorithms for separable nonnegative matrix factorization
Gillis, N. and Vavasis, S. A · 2013
Earlier work this paper cites.
Non-negative matrix factorization revisited: Uniqueness and algorithm for symmetric decomposition
Huang, K., Sidiropoulos, N. D., and Swami, A · 2013
Cited alongside, same era.
A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion
Xu, Y. and Yin, W · 2013
Cited alongside, same era.
Learning to learn by gradient descent by gradient descent
Andrychowicz, M., Denil, M., Colmenarejo, S. G., Hoffman, M. W., Pfau, D., Schaul, T., Shillingford, B., and de Freitas, N · 2016
Cited alongside, same era.
Ba, J. L., Kiros, J. R., and Hinton, G. E · 2016
Cited alongside, same era.
A flexible and efficient algorithmic framework for constrained matrix and tensor factorization
Huang, K., Sidiropoulos, N. D., and Liavas, A. P · 2016
Cited alongside, same era.
Hyperspectral unmixing: Ground truth labeling, datasets, benchmark performances and survey
Zhu, F · 2017
Later among the works it cites.
Stochastic training of graph convolutional networks with variance reduction
Chen, J., Zhu, J., and Song, L · 2018
Later among the works it cites.
Self-attention with relative position representations
Shaw, P., Uszkoreit, J., and Vaswani, A · 2018
Later among the works it cites.
Differentiable convex optimization layers
Agrawal, A., Amos, B., Barratt, S., Boyd, S., Diamond, S., and Kolter, J. Z · 2019
Later among the works it cites.
Fast graph representation learning with PyTorch Geometric
Fey, M. and Lenssen, J. E · 2019
Later among the works it cites.
Nonnegative matrix factorization for signal and data analytics: Identifiability, algorithms, and applications
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Li, K. and Malik, J · 2016
Cited alongside, same era.
Sgdr: Stochastic gradient descent with warm restarts
Loshchilov, I. and Hutter, F · 2016
Cited alongside, same era.
Generalized low rank models
Udell, M., Horn, C., Zadeh, R., Boyd, S., et al · 2016
Cited alongside, same era.
Neural optimizer search with reinforcement learning
Bello, I., Zoph, B., Vasudevan, V., and Le, Q. V · 2017
Cited alongside, same era.
Graph convolutional matrix completion
Berg, R. v. d., Kipf, T. N., and Welling, M · 2017
Cited alongside, same era.
Geometric deep learning: going beyond euclidean data
Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., and Vandergheynst, P · 2017
Cited alongside, same era.
Learning combinatorial optimization algorithms over graphs
Dai, H., Khalil, E., Zhang, Y., Dilkina, B., and Song, L · 2017
Cited alongside, same era.
Fu, X., Huang, K., Sidiropoulos, N. D., and Ma, W.-K · 2019
Later among the works it cites.
Exact combinatorial optimization with graph convolutional neural networks
Gasse, M., Chételat, D., Ferroni, N., Charlin, L., and Lodi, A · 2019
Later among the works it cites.
Automated machine learning: methods, systems, challenges
Hutter, F., Kotthoff, L., and Vanschoren, J · 2019
Later among the works it cites.
Data-driven nonsmooth optimization
Banert, S., Ringh, A., Adler, J., Karlsson, J., and Oktem, O · 2020
Later among the works it cites.
Nonnegative Matrix Factorization
Gillis, N · 2020
Later among the works it cites.
Reformer: The efficient transformer
Kitaev, N., Kaiser, L., and Levskaya, A · 2020
Later among the works it cites.
Reverse engineering learned optimizers reveals known and novel mechanisms
Maheswaranathan, N., Sussillo, D., Metz, L., Sun, R., and Sohl-Dickstein, J · 2020
Later among the works it cites.
Solving mixed integer programs using neural networks
Nair, V., Bartunov, S., Gimeno, F., von Glehn, I., Lichocki, P., Lobov, I., O’Donoghue, B., Sonnerat, N., Tjandraatmadja, C., Wang, P., et al · 2020
Later among the works it cites.
BiG-transformer: Integrating hierarchical features for transformer via bipartite graph
Shu, X., Xue, M., Li, Y., Zhang, Z., and Liu, T · 2020
Later among the works it cites.
GraphSAINT: Graph sampling based inductive learning method
Zeng, H., Zhou, H., Srivastava, A., Kannan, R., and Prasanna, V · 2020
Later among the works it cites.
Combinatorial optimization and reasoning with graph neural networks
Cappart, Q., Chételat, D., Khalil, E., Lodi, A., Morris, C., and Veličković, P · 2021
Later among the works it cites.
Learning to optimize: A primer and a benchmark
Chen, T., Chen, X., Chen, W., Heaton, H., Liu, J., Wang, Z., and Yin, W · 2021
Later among the works it cites.
Generative adversarial transformers
Hudson, D. A. and Zitnick, C. L · 2021
Later among the works it cites.
Training graph neural networks with 1000 layers
Li, G., Müller, M., Ghanem, B., and Koltun, V · 2021
Later among the works it cites.
Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing
Monga, V., Li, Y., and Eldar, Y. C · 2021
Later among the works it cites.
Neural fixed-point acceleration for convex optimization
Venkataraman, S. and Amos, B · 2021
Later among the works it cites.