Sorry, you need to enable JavaScript to visit this website.

Graph Signal Processing

Aggregation Graph Neural Networks


Graph neural networks (GNNs) regularize classical neural networks by exploiting the underlying irregular structure supporting graph data, extending its application to broader data domains. The aggregation GNN presented here is a novel GNN that exploits the fact that the data collected at a single node by means of successive local exchanges with neighbors exhibits a regular structure. Thus, regular convolution and regular pooling yield an appropriately regularized GNN.

Paper Details

Authors:
Fernando Gama, Antonio G. Marques, Geert Leus, Alejandro Ribeiro
Submitted On:
15 May 2019 - 2:34pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

aggregationICASSP19slides.pdf

(15)

Keywords

Additional Categories

Subscribe

[1] Fernando Gama, Antonio G. Marques, Geert Leus, Alejandro Ribeiro, "Aggregation Graph Neural Networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4528. Accessed: Jun. 25, 2019.
@article{4528-19,
url = {http://sigport.org/4528},
author = {Fernando Gama; Antonio G. Marques; Geert Leus; Alejandro Ribeiro },
publisher = {IEEE SigPort},
title = {Aggregation Graph Neural Networks},
year = {2019} }
TY - EJOUR
T1 - Aggregation Graph Neural Networks
AU - Fernando Gama; Antonio G. Marques; Geert Leus; Alejandro Ribeiro
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4528
ER -
Fernando Gama, Antonio G. Marques, Geert Leus, Alejandro Ribeiro. (2019). Aggregation Graph Neural Networks. IEEE SigPort. http://sigport.org/4528
Fernando Gama, Antonio G. Marques, Geert Leus, Alejandro Ribeiro, 2019. Aggregation Graph Neural Networks. Available at: http://sigport.org/4528.
Fernando Gama, Antonio G. Marques, Geert Leus, Alejandro Ribeiro. (2019). "Aggregation Graph Neural Networks." Web.
1. Fernando Gama, Antonio G. Marques, Geert Leus, Alejandro Ribeiro. Aggregation Graph Neural Networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4528

Fast Sampling of Graph Signals with Noise via Neumann Series Conversion


Graph sampling with independent noise towards minimum mean square error (MMSE)
leads to the known A-optimality criterion, which is computation-intensive to
evaluate and NP-hard to optimize. In this paper, we propose a new low complexity
sampling strategy based on Neumann series that circumvents large matrix
inversion and eigen-decomposition. We first prove that a DC-shifted A-optimality
criterion is equivalent to an objective computed using the inverse of a
sub-matrix of an ideal graph low-pass (LP) filter. The LP filter matrix can be

Paper Details

Authors:
Gene Cheung; Yongchao Wang
Submitted On:
8 May 2019 - 12:17pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

A-optimal graph sampling

(11)

Keywords

Additional Categories

Subscribe

[1] Gene Cheung; Yongchao Wang, "Fast Sampling of Graph Signals with Noise via Neumann Series Conversion", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4121. Accessed: Jun. 25, 2019.
@article{4121-19,
url = {http://sigport.org/4121},
author = {Gene Cheung; Yongchao Wang },
publisher = {IEEE SigPort},
title = {Fast Sampling of Graph Signals with Noise via Neumann Series Conversion},
year = {2019} }
TY - EJOUR
T1 - Fast Sampling of Graph Signals with Noise via Neumann Series Conversion
AU - Gene Cheung; Yongchao Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4121
ER -
Gene Cheung; Yongchao Wang. (2019). Fast Sampling of Graph Signals with Noise via Neumann Series Conversion. IEEE SigPort. http://sigport.org/4121
Gene Cheung; Yongchao Wang, 2019. Fast Sampling of Graph Signals with Noise via Neumann Series Conversion. Available at: http://sigport.org/4121.
Gene Cheung; Yongchao Wang. (2019). "Fast Sampling of Graph Signals with Noise via Neumann Series Conversion." Web.
1. Gene Cheung; Yongchao Wang. Fast Sampling of Graph Signals with Noise via Neumann Series Conversion [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4121

MODELING SIGNALS OVER DIRECTED GRAPHS THROUGH FILTERING


In this paper, we discuss the problem of modeling a graph signal on a directed graph when observing only partially the graph signal. The graph signal is recovered using a learned graph filter. The novelty is to use the random walk operator associated to an ergodic random walk on the graph, so as to define and learn a graph filter, expressed as a polynomial of this operator. Through the study of different cases, we show the efficiency of the signal modeling using the random walk operator compared to existing methods using the adjacency matrix or ignoring the directions in the graph.

Paper Details

Authors:
Harry Sevi, Gabriel Rilling, Pierre Borgnat
Submitted On:
27 November 2018 - 9:53am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Borgnat_talk_GlobalSIP_2018.pdf

(50)

Keywords

Additional Categories

Subscribe

[1] Harry Sevi, Gabriel Rilling, Pierre Borgnat, "MODELING SIGNALS OVER DIRECTED GRAPHS THROUGH FILTERING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3812. Accessed: Jun. 25, 2019.
@article{3812-18,
url = {http://sigport.org/3812},
author = {Harry Sevi; Gabriel Rilling; Pierre Borgnat },
publisher = {IEEE SigPort},
title = {MODELING SIGNALS OVER DIRECTED GRAPHS THROUGH FILTERING},
year = {2018} }
TY - EJOUR
T1 - MODELING SIGNALS OVER DIRECTED GRAPHS THROUGH FILTERING
AU - Harry Sevi; Gabriel Rilling; Pierre Borgnat
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3812
ER -
Harry Sevi, Gabriel Rilling, Pierre Borgnat. (2018). MODELING SIGNALS OVER DIRECTED GRAPHS THROUGH FILTERING. IEEE SigPort. http://sigport.org/3812
Harry Sevi, Gabriel Rilling, Pierre Borgnat, 2018. MODELING SIGNALS OVER DIRECTED GRAPHS THROUGH FILTERING. Available at: http://sigport.org/3812.
Harry Sevi, Gabriel Rilling, Pierre Borgnat. (2018). "MODELING SIGNALS OVER DIRECTED GRAPHS THROUGH FILTERING." Web.
1. Harry Sevi, Gabriel Rilling, Pierre Borgnat. MODELING SIGNALS OVER DIRECTED GRAPHS THROUGH FILTERING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3812

Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs

Paper Details

Authors:
Madeleine S. Kotzagiannidis, Mike E. Davies
Submitted On:
8 December 2018 - 1:41pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

MKotzagiannidisglobalsip2018.pdf

(57)

Keywords

Additional Categories

Subscribe

[1] Madeleine S. Kotzagiannidis, Mike E. Davies, "Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3802. Accessed: Jun. 25, 2019.
@article{3802-18,
url = {http://sigport.org/3802},
author = {Madeleine S. Kotzagiannidis; Mike E. Davies },
publisher = {IEEE SigPort},
title = {Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs},
year = {2018} }
TY - EJOUR
T1 - Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs
AU - Madeleine S. Kotzagiannidis; Mike E. Davies
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3802
ER -
Madeleine S. Kotzagiannidis, Mike E. Davies. (2018). Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs. IEEE SigPort. http://sigport.org/3802
Madeleine S. Kotzagiannidis, Mike E. Davies, 2018. Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs. Available at: http://sigport.org/3802.
Madeleine S. Kotzagiannidis, Mike E. Davies. (2018). "Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs." Web.
1. Madeleine S. Kotzagiannidis, Mike E. Davies. Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3802

Predicting Power Outages Using Graph Neural Networks


Power outages have a major impact on economic development due to the dependence of (virtually all) productive sectors on electric power. Thus, many resources within the scientific and engineering communities have been employed to improve the efficiency and reliability of power grids. In particular, we consider the problem of predicting power outages based on the current weather conditions. Weather measurements taken by a sensor network naturally fit within the graph signal processing framework since the measurements are related by the relative position of the sensors.

Paper Details

Authors:
Damian Owerko, Fernando Gama, Alejandro Ribeiro
Submitted On:
26 November 2018 - 10:11pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

globalsip_2018_poster.pdf

(81)

Keywords

Additional Categories

Subscribe

[1] Damian Owerko, Fernando Gama, Alejandro Ribeiro, "Predicting Power Outages Using Graph Neural Networks", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3800. Accessed: Jun. 25, 2019.
@article{3800-18,
url = {http://sigport.org/3800},
author = {Damian Owerko; Fernando Gama; Alejandro Ribeiro },
publisher = {IEEE SigPort},
title = {Predicting Power Outages Using Graph Neural Networks},
year = {2018} }
TY - EJOUR
T1 - Predicting Power Outages Using Graph Neural Networks
AU - Damian Owerko; Fernando Gama; Alejandro Ribeiro
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3800
ER -
Damian Owerko, Fernando Gama, Alejandro Ribeiro. (2018). Predicting Power Outages Using Graph Neural Networks. IEEE SigPort. http://sigport.org/3800
Damian Owerko, Fernando Gama, Alejandro Ribeiro, 2018. Predicting Power Outages Using Graph Neural Networks. Available at: http://sigport.org/3800.
Damian Owerko, Fernando Gama, Alejandro Ribeiro. (2018). "Predicting Power Outages Using Graph Neural Networks." Web.
1. Damian Owerko, Fernando Gama, Alejandro Ribeiro. Predicting Power Outages Using Graph Neural Networks [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3800

Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs

Paper Details

Authors:
Madeleine Kotzagiannidis, Mike E. Davies
Submitted On:
27 March 2019 - 9:05am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

MKotzagiannidisglobalsip2018.pdf

(19)

Keywords

Additional Categories

Subscribe

[1] Madeleine Kotzagiannidis, Mike E. Davies, "Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3799. Accessed: Jun. 25, 2019.
@article{3799-18,
url = {http://sigport.org/3799},
author = {Madeleine Kotzagiannidis; Mike E. Davies },
publisher = {IEEE SigPort},
title = {Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs},
year = {2018} }
TY - EJOUR
T1 - Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs
AU - Madeleine Kotzagiannidis; Mike E. Davies
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3799
ER -
Madeleine Kotzagiannidis, Mike E. Davies. (2018). Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs. IEEE SigPort. http://sigport.org/3799
Madeleine Kotzagiannidis, Mike E. Davies, 2018. Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs. Available at: http://sigport.org/3799.
Madeleine Kotzagiannidis, Mike E. Davies. (2018). "Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs." Web.
1. Madeleine Kotzagiannidis, Mike E. Davies. Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3799

Rumour Source Detection in Social Networks using Partial Observations

Paper Details

Authors:
Submitted On:
22 November 2018 - 9:30am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

globalsip18.pdf

(64)

Keywords

Additional Categories

Subscribe

[1] , "Rumour Source Detection in Social Networks using Partial Observations", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3716. Accessed: Jun. 25, 2019.
@article{3716-18,
url = {http://sigport.org/3716},
author = { },
publisher = {IEEE SigPort},
title = {Rumour Source Detection in Social Networks using Partial Observations},
year = {2018} }
TY - EJOUR
T1 - Rumour Source Detection in Social Networks using Partial Observations
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3716
ER -
. (2018). Rumour Source Detection in Social Networks using Partial Observations. IEEE SigPort. http://sigport.org/3716
, 2018. Rumour Source Detection in Social Networks using Partial Observations. Available at: http://sigport.org/3716.
. (2018). "Rumour Source Detection in Social Networks using Partial Observations." Web.
1. . Rumour Source Detection in Social Networks using Partial Observations [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3716

Convolutional Neural Networks via Node-Varying Graph Filters


Convolutional neural networks (CNNs) are being applied to an increasing number of problems and fields due to their superior performance in classification and regression tasks. Since two of the key operations that CNNs implement are convolution and pooling, this type of networks is implicitly designed to act on data described by regular structures such as images. Motivated by the recent interest in processing signals defined in irregular domains, we advocate a CNN architecture that operates on signals supported on graphs.

Paper Details

Authors:
Fernando Gama, Geert Leus, Antonio Marques, Alejandro Ribeiro
Submitted On:
31 May 2018 - 7:03pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

gama-leus-marques-ribeiro-node_variant_graph_filter.pdf

(137)

Keywords

Additional Categories

Subscribe

[1] Fernando Gama, Geert Leus, Antonio Marques, Alejandro Ribeiro, "Convolutional Neural Networks via Node-Varying Graph Filters", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3226. Accessed: Jun. 25, 2019.
@article{3226-18,
url = {http://sigport.org/3226},
author = {Fernando Gama; Geert Leus; Antonio Marques; Alejandro Ribeiro },
publisher = {IEEE SigPort},
title = {Convolutional Neural Networks via Node-Varying Graph Filters},
year = {2018} }
TY - EJOUR
T1 - Convolutional Neural Networks via Node-Varying Graph Filters
AU - Fernando Gama; Geert Leus; Antonio Marques; Alejandro Ribeiro
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3226
ER -
Fernando Gama, Geert Leus, Antonio Marques, Alejandro Ribeiro. (2018). Convolutional Neural Networks via Node-Varying Graph Filters. IEEE SigPort. http://sigport.org/3226
Fernando Gama, Geert Leus, Antonio Marques, Alejandro Ribeiro, 2018. Convolutional Neural Networks via Node-Varying Graph Filters. Available at: http://sigport.org/3226.
Fernando Gama, Geert Leus, Antonio Marques, Alejandro Ribeiro. (2018). "Convolutional Neural Networks via Node-Varying Graph Filters." Web.
1. Fernando Gama, Geert Leus, Antonio Marques, Alejandro Ribeiro. Convolutional Neural Networks via Node-Varying Graph Filters [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3226

Control of Graph Signals over Random Time-Varying Graphs


In this work, we jointly exploit tools from graph signal processing and control theory to drive a bandlimited graph signal that is being diffused on a random time-varying graph from a subset of nodes. As our main contribution, we rely only on the statistics of the graph to introduce the concept of controllability in the mean, and therefore drive the signal on the expected graph to a desired state.

Paper Details

Authors:
Fernando Gama, Elvin Isufi, Geert Leus and Alejandro Ribeiro
Submitted On:
19 April 2018 - 7:37pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

control-icassp18-poster.pdf

(137)

Keywords

Additional Categories

Subscribe

[1] Fernando Gama, Elvin Isufi, Geert Leus and Alejandro Ribeiro, "Control of Graph Signals over Random Time-Varying Graphs", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3041. Accessed: Jun. 25, 2019.
@article{3041-18,
url = {http://sigport.org/3041},
author = {Fernando Gama; Elvin Isufi; Geert Leus and Alejandro Ribeiro },
publisher = {IEEE SigPort},
title = {Control of Graph Signals over Random Time-Varying Graphs},
year = {2018} }
TY - EJOUR
T1 - Control of Graph Signals over Random Time-Varying Graphs
AU - Fernando Gama; Elvin Isufi; Geert Leus and Alejandro Ribeiro
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3041
ER -
Fernando Gama, Elvin Isufi, Geert Leus and Alejandro Ribeiro. (2018). Control of Graph Signals over Random Time-Varying Graphs. IEEE SigPort. http://sigport.org/3041
Fernando Gama, Elvin Isufi, Geert Leus and Alejandro Ribeiro, 2018. Control of Graph Signals over Random Time-Varying Graphs. Available at: http://sigport.org/3041.
Fernando Gama, Elvin Isufi, Geert Leus and Alejandro Ribeiro. (2018). "Control of Graph Signals over Random Time-Varying Graphs." Web.
1. Fernando Gama, Elvin Isufi, Geert Leus and Alejandro Ribeiro. Control of Graph Signals over Random Time-Varying Graphs [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3041

Demixing and blind deconvolution of graph-diffused signals


We extend the classical joint problem of signal demixing, blind deconvolution,
and filter identification to the realm of graphs. The model is that
each mixing signal is generated by a sparse input diffused via a graph filter.
Then, the sum of diffused signals is observed. We identify and address
two problems: 1) each sparse input is diffused in a different graph; and 2)
all signals are diffused in the same graph. These tasks amount to finding
the collections of sources and filter coefficients producing the observation.

Paper Details

Authors:
Fernando J. Iglesias, Santiago Segarra, Samuel Rey-Escudero, Antonio G. Marques, David Ramirez
Submitted On:
19 April 2018 - 4:51pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_demixing_GSP_poster_v2.pdf

(229)

Subscribe

[1] Fernando J. Iglesias, Santiago Segarra, Samuel Rey-Escudero, Antonio G. Marques, David Ramirez, "Demixing and blind deconvolution of graph-diffused signals", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3027. Accessed: Jun. 25, 2019.
@article{3027-18,
url = {http://sigport.org/3027},
author = {Fernando J. Iglesias; Santiago Segarra; Samuel Rey-Escudero; Antonio G. Marques; David Ramirez },
publisher = {IEEE SigPort},
title = {Demixing and blind deconvolution of graph-diffused signals},
year = {2018} }
TY - EJOUR
T1 - Demixing and blind deconvolution of graph-diffused signals
AU - Fernando J. Iglesias; Santiago Segarra; Samuel Rey-Escudero; Antonio G. Marques; David Ramirez
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3027
ER -
Fernando J. Iglesias, Santiago Segarra, Samuel Rey-Escudero, Antonio G. Marques, David Ramirez. (2018). Demixing and blind deconvolution of graph-diffused signals. IEEE SigPort. http://sigport.org/3027
Fernando J. Iglesias, Santiago Segarra, Samuel Rey-Escudero, Antonio G. Marques, David Ramirez, 2018. Demixing and blind deconvolution of graph-diffused signals. Available at: http://sigport.org/3027.
Fernando J. Iglesias, Santiago Segarra, Samuel Rey-Escudero, Antonio G. Marques, David Ramirez. (2018). "Demixing and blind deconvolution of graph-diffused signals." Web.
1. Fernando J. Iglesias, Santiago Segarra, Samuel Rey-Escudero, Antonio G. Marques, David Ramirez. Demixing and blind deconvolution of graph-diffused signals [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3027

Pages