Learning of structured graph dictionaries

By Xuan Zhang, Xiaowen Dong, Pascal Frossard. 2012

45 citations recorded by the source corpus.

Subfields: Computational Mechanics, Electrical and Electronic Engineering, Graph Learning, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Michael M. Bronstein
2. Emanuele Rodolà
3. Federico Monti
4. Jonathan Masci
5. Davide Boscaini
6. M. Ovsjanikov
7. Pierre Vandergheynst
8. Leonidas J. Guibas

In Electrical and Electronic Engineering

1. José M. F. Moura
2. Siheng Chen
3. Pierre Vandergheynst
4. Pascal Frossard
5. Michael M. Bronstein
6. Michael G. Rabbat
7. Aliaksei Sandryhaila
8. Jonathan Masci

In Graph Learning

1. Michael M. Bronstein
2. Federico Monti
3. Pierre Vandergheynst
4. José M. F. Moura
5. Pascal Frossard
6. Xavier Bresson
7. Aliaksei Sandryhaila
8. Stephan Günnemann

In Signal Processing

1. Federico Monti
2. Michael M. Bronstein
3. Siheng Chen
4. Aliaksei Sandryhaila
5. José M. F. Moura
6. Pierre Vandergheynst
7. Pascal Frossard
8. Jonathan Masci

Citations in the corpus

• Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, methodology): “idering the orthogonal eigenfunctions of the Laplacian operator as a generalization of the Fourier basis. Constructions such as wavelets [14, 18, 21, 39, 45] or algorithms such as dictionary learning [62], Lasso [9], PCA [43, 44], or matrix completion [23] originally developed for the Euclidean doma”
• Learning Laplacian Matrix in Smooth Graph Signal Representations (2014, background): “Representative works include studies on the generalizations of the Fourier transform [9], [10], the wavelet transform [11]–[16], dictionary learning methods [17], [18], and time-frequency analysis [19], [20] on graphs, with applications to image processing [21], brain network classification [22], mo”
• Signal Recovery on Graphs: Variation Minimization (2014, background): “…involves graph-based filtering [3], [7], [8], graph-based transforms [3], [6], [9], sampling and interpolation on graphs [10]–[12], uncertainty principle on graphs [13], semi-supervised classification on graphs [14]–[16], graph dictionary learning [17], [18], and community detection on graphs [19].”
• Learning Graphs From Data: A Signal Representation Perspective (2018, background): “51 IEEE SIgnal ProcESSIng MagazInE | May 2019 | trained by taking into account information from both G and x [37], [38].”
• Wavelets on Graphs via Deep Learning (2013, background): “An interesting direction for future research would be to randomize the graph partitioning process or to use bagging over training functions in order to obtain a family of wavelet constructions on the same graph – leading to overcomplete dictionaries like in [25].”