1 code implementation • 19 Dec 2009 • David K Hammond, Pierre Vandergheynst, Rémi Gribonval
We propose a novel method for constructing wavelet transforms of functions defined on the vertices of an arbitrary finite weighted graph.
Functional Analysis Information Theory Information Theory 42C40; 65T90
1 code implementation • 31 Oct 2012 • David I Shuman, Sunil K. Narang, Pascal Frossard, Antonio Ortega, Pierre Vandergheynst
In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs.
no code implementations • 13 Dec 2012 • Gilles Puy, Pierre Vandergheynst
The background image is common to all observed images but undergoes geometric transformations, as the scene is observed from different viewpoints.
no code implementations • 9 Dec 2013 • Mike Davies, Gilles Puy, Pierre Vandergheynst, Yves Wiaux
Inspired by the recently proposed Magnetic Resonance Fingerprinting (MRF) technique, we develop a principled compressed sensing framework for quantitative MRI.
Information Theory Information Theory
no code implementations • 4 Feb 2014 • Nathanael Perraudin, Vassilis Kalofolias, David Shuman, Pierre Vandergheynst
Convex optimization is an essential tool for machine learning, as many of its problems can be formulated as minimization problems of specific objective functions.
2 code implementations • 30 Jun 2014 • Xiaowen Dong, Dorina Thanou, Pascal Frossard, Pierre Vandergheynst
We show that the Gaussian prior leads to an efficient representation that favors the smoothness property of the graph signals.
2 code implementations • 7 Aug 2014 • Vassilis Kalofolias, Xavier Bresson, Michael Bronstein, Pierre Vandergheynst
Our main goal is thus to find a low-rank solution that is structured by the proximities of rows and columns encoded by graphs.
Ranked #15 on Recommendation Systems on MovieLens 100K (using extra training data)
no code implementations • CVPR 2015 • Artiom Kovnatsky, Michael M. Bronstein, Xavier Bresson, Pierre Vandergheynst
In this paper, we consider the problem of finding dense intrinsic correspondence between manifolds using the recently introduced functional framework.
no code implementations • 26 Jan 2015 • Jonathan Masci, Davide Boscaini, Michael M. Bronstein, Pierre Vandergheynst
Feature descriptors play a crucial role in a wide range of geometry analysis and processing applications, including shape correspondence, retrieval, and segmentation.
no code implementations • ICCV 2015 • Nauman Shahid, Vassilis Kalofolias, Xavier Bresson, Michael Bronstein, Pierre Vandergheynst
Principal Component Analysis (PCA) is the most widely used tool for linear dimensionality reduction and clustering.
no code implementations • 29 Jul 2015 • Nauman Shahid, Nathanael Perraudin, Vassilis Kalofolias, Gilles Puy, Pierre Vandergheynst
Clustering experiments on 7 benchmark datasets with different types of corruptions and background separation experiments on 3 video datasets show that our proposed model outperforms 10 state-of-the-art dimensionality reduction models.
no code implementations • 15 Sep 2015 • Ana Susnjara, Nathanael Perraudin, Daniel Kressner, Pierre Vandergheynst
Signal-processing on graphs has developed into a very active field of research during the last decade.
Numerical Analysis
no code implementations • 29 Sep 2015 • Nicolas Tremblay, Gilles Puy, Pierre Borgnat, Remi Gribonval, Pierre Vandergheynst
We build upon recent advances in graph signal processing to propose a faster spectral clustering algorithm.
Social and Information Networks Numerical Analysis
no code implementations • 16 Nov 2015 • Yann Schoenenberger, Johan Paratte, Pierre Vandergheynst
Noisy 3D point clouds arise in many applications.
no code implementations • 16 Nov 2015 • Gilles Puy, Nicolas Tremblay, Rémi Gribonval, Pierre Vandergheynst
On the contrary, the second strategy is adaptive but yields optimal results.
1 code implementation • 8 Jan 2016 • Kirell Benzi, Vassilis Kalofolias, Xavier Bresson, Pierre Vandergheynst
This work formulates a novel song recommender system as a matrix completion problem that benefits from collaborative filtering through Non-negative Matrix Factorization (NMF) and content-based filtering via total variation (TV) on graphs.
no code implementations • 11 Jan 2016 • Nathanaël Perraudin, Pierre Vandergheynst
Graphs are a central tool in machine learning and information processing as they allow to conveniently capture the structure of complex datasets.
no code implementations • 5 Feb 2016 • Nauman Shahid, Nathanael Perraudin, Gilles Puy, Pierre Vandergheynst
We introduce a novel framework for an approxi- mate recovery of data matrices which are low-rank on graphs, from sampled measurements.
no code implementations • 5 Feb 2016 • Nicolas Tremblay, Gilles Puy, Remi Gribonval, Pierre Vandergheynst
Spectral clustering has become a popular technique due to its high performance in many contexts.
no code implementations • 10 Mar 2016 • Nathanael Perraudin, Benjamin Ricaud, David Shuman, Pierre Vandergheynst
Accordingly, we suggest a new way to incorporate a notion of locality, and develop local uncertainty principles that bound the concentration of the analysis coefficients of each atom of a localized graph spectral filter frame in terms of quantities that depend on the local structure of the graph around the center vertex of the given atom.
no code implementations • 14 Mar 2016 • Faisal Mahmood, Nauman Shahid, Pierre Vandergheynst, Ulf Skoglund
This makes the sinogram an ideal candidate for graph based denoising since it generally has a piecewise smooth structure.
1 code implementation • 24 Mar 2016 • Rodrigo Pena, Xavier Bresson, Pierre Vandergheynst
We cast the problem of source localization on graphs as the simultaneous problem of sparse recovery and diffusion kernel learning.
no code implementations • 18 May 2016 • Nauman Shahid, Nathanael Perraudin, Pierre Vandergheynst
Many real world datasets subsume a linear or non-linear low-rank structure in a very low-dimensional space.
no code implementations • 22 Jun 2016 • Nathanael Perraudin, Andreas Loukas, Francesco Grassi, Pierre Vandergheynst
Graph-based methods for signal processing have shown promise for the analysis of data exhibiting irregular structure, such as those found in social, transportation, and sensor networks.
4 code implementations • NeurIPS 2016 • Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst
In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs.
Ranked #4 on Skeleton Based Action Recognition on SBU
no code implementations • 4 Oct 2016 • Faisal Mahmood, Nauman Shahid, Ulf Skoglund, Pierre Vandergheynst
Sparsity exploiting image reconstruction (SER) methods have been extensively used with Total Variation (TV) regularization for tomographic reconstructions.
no code implementations • 15 Nov 2016 • Nauman Shahid, Francesco Grassi, Pierre Vandergheynst
We propose a new framework for the analysis of low-rank tensors which lies at the intersection of spectral graph theory and signal processing.
no code implementations • 24 Nov 2016 • Michael M. Bronstein, Joan Bruna, Yann Lecun, Arthur Szlam, Pierre Vandergheynst
In many applications, such geometric data are large and complex (in the case of social networks, on the scale of billions), and are natural targets for machine learning techniques.
16 code implementations • ISMIR 2017 • Michaël Defferrard, Kirell Benzi, Pierre Vandergheynst, Xavier Bresson
We introduce the Free Music Archive (FMA), an open and easily accessible dataset suitable for evaluating several tasks in MIR, a field concerned with browsing, searching, and organizing large music collections.
5 code implementations • 22 Dec 2016 • Youngjoo Seo, Michaël Defferrard, Pierre Vandergheynst, Xavier Bresson
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data.
no code implementations • 19 Feb 2017 • Johan Paratte, Nathanaël Perraudin, Pierre Vandergheynst
Visualizing high-dimensional data has been a focus in data analysis communities for decades, which has led to the design of many algorithms, some of which are now considered references (such as t-SNE for example).
no code implementations • ICML 2018 • Lionel Martin, Andreas Loukas, Pierre Vandergheynst
Spectral clustering is a widely studied problem, yet its complexity is prohibitive for dynamic graphs of even modest size.
1 code implementation • 1 Oct 2017 • Volodymyr Miz, Kirell Benzi, Benjamin Ricaud, Pierre Vandergheynst
The model exploits collective effect of the dynamics to discover events.
2 code implementations • 1 Dec 2017 • Antonio Ortega, Pascal Frossard, Jelena Kovačević, José M. F. Moura, Pierre Vandergheynst
Research in Graph Signal Processing (GSP) aims to develop tools for processing data defined on irregular graph domains.
Signal Processing
1 code implementation • 30 Dec 2017 • Konstantinos Pitas, Mike Davies, Pierre Vandergheynst
Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers.
no code implementations • ICLR 2018 • Konstantinos Pitas, Mike Davies, Pierre Vandergheynst
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers often with little or no drop in classification accuracy.
no code implementations • 16 Feb 2018 • Helena Peić Tukuljac, Thach Pham Vu, Hervé Lissek, Pierre Vandergheynst
Acoustical behavior of a room for a given position of microphone and sound source is usually described using the room impulse response.
no code implementations • ICML 2018 • Andreas Loukas, Pierre Vandergheynst
How does coarsening affect the spectrum of a general graph?
1 code implementation • 12 Mar 2018 • Konstantinos Pitas, Mike Davies, Pierre Vandergheynst
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy.
2 code implementations • 22 Jan 2019 • Volodymyr Miz, Benjamin Ricaud, Kirell Benzi, Pierre Vandergheynst
We define an anomaly as a localized increase in temporal activity in a cluster of nodes.
1 code implementation • 20 Mar 2019 • Nicolas Aspert, Volodymyr Miz, Benjamin Ricaud, Pierre Vandergheynst
It makes the parsing and extraction of relevant information cumbersome.
no code implementations • 21 May 2019 • Konstantinos Pitas, Mike Davies, Pierre Vandergheynst
Recently developed smart pruning algorithms use the DNN response over the training set for a variety of cost functions to determine redundant network weights, leading to less accuracy degradation and possibly less retraining time.
no code implementations • 23 May 2019 • Konstantinos Pitas, Andreas Loukas, Mike Davies, Pierre Vandergheynst
Deep convolutional neural networks (CNNs) have been shown to be able to fit a random labeling over data while still being able to generalize well for normal labels.
no code implementations • 25 Sep 2019 • Helena Peic Tukuljac, Benjamin Ricaud, Nicolas Aspert, Pierre Vandergheynst
This layer aims at being the input layer of convolutional neural networks for audio applications.
1 code implementation • 17 Feb 2020 • Volodymyr Miz, Joëlle Hanna, Nicolas Aspert, Benjamin Ricaud, Pierre Vandergheynst
In this work, we propose an automatic evaluation and comparison of the browsing behavior of Wikipedia readers that can be applied to any language editions of Wikipedia.
Social and Information Networks Computers and Society
2 code implementations • 31 May 2022 • Daniele Grattarola, Pierre Vandergheynst
We consider the problem of learning implicit neural representations (INRs) for signals on non-Euclidean domains.
1 code implementation • 6 Apr 2023 • Adam Gosztolai, Robert L. Peach, Alexis Arnaudon, Mauricio Barahona, Pierre Vandergheynst
The dynamics of neuron populations during many behavioural tasks evolve on low-dimensional manifolds.
1 code implementation • 28 Sep 2023 • Robert L. Peach, Matteo Vinao-Carl, Nir Grossman, Michael David, Emma Mallas, David Sharp, Paresh A. Malhotra, Pierre Vandergheynst, Adam Gosztolai
Gaussian processes (GPs) are popular nonparametric statistical models for learning unknown functions and quantifying the spatiotemporal uncertainty in data.