Search Results for author: Pierre Vandergheynst

Found 44 papers, 16 papers with code

What is Trending on Wikipedia? Capturing Trends and Language Biases Across Wikipedia Editions

1 code implementation17 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

The role of invariance in spectral complexity-based generalization bounds

no code implementations23 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.

Generalization Bounds

Revisiting hard thresholding for DNN pruning

no code implementations21 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.

A Graph-structured Dataset for Wikipedia Research

1 code implementation20 Mar 2019 Nicolas Aspert, Volodymyr Miz, Benjamin Ricaud, Pierre Vandergheynst

It makes the parsing and extraction of relevant information cumbersome.

FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees

1 code implementation12 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.

General Classification

Joint Estimation of Room Geometry and Modes with Compressed Sensing

no code implementations16 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.

Cheap DNN Pruning with Performance Guarantees

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.

Classification General Classification

PAC-Bayesian Margin Bounds for Convolutional Neural Networks

1 code implementation30 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.

Graph Signal Processing: Overview, Challenges and Applications

1 code implementation1 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

Fast Approximate Spectral Clustering for Dynamic Networks

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.

Compressive Embedding and Visualization using Graphs

no code implementations19 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).

Structured Sequence Modeling with Graph Convolutional Recurrent Networks

5 code implementations22 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.

Language Modelling

FMA: A Dataset For Music Analysis

12 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.

Geometric deep learning: going beyond Euclidean data

no code implementations24 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.

Multilinear Low-Rank Tensors on Graphs & Applications

no code implementations15 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.


Adaptive Graph-based Total Variation for Tomographic Reconstructions

no code implementations4 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.

Image Reconstruction Tomographic Reconstructions

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

5 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.

Node Classification Skeleton Based Action Recognition

Towards stationary time-vertex signal processing

no code implementations22 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.


Low-Rank Matrices on Graphs: Generalized Recovery & Applications

no code implementations18 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.

Source Localization on Graphs via l1 Recovery and Spectral Graph Theory

1 code implementation24 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.

Graph Based Sinogram Denoising for Tomographic Reconstructions

no code implementations14 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.

Denoising Tomographic Reconstructions

Global and Local Uncertainty Principles for Signals on Graphs

no code implementations10 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.

Compressive Spectral Clustering

no code implementations5 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.

Compressive PCA for Low-Rank Matrices on Graphs

no code implementations5 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.

Stationary signal processing on graphs

no code implementations11 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.

Denoising Translation

Song Recommendation with Non-Negative Matrix Factorization and Graph Total Variation

1 code implementation8 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.

Collaborative Filtering Matrix Completion +1

Random sampling of bandlimited signals on graphs

no code implementations16 Nov 2015 Gilles Puy, Nicolas Tremblay, Rémi Gribonval, Pierre Vandergheynst

On the contrary, the second strategy is adaptive but yields optimal results.

Accelerated Spectral Clustering Using Graph Filtering Of Random Signals

no code implementations29 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

Accelerated filtering on graphs using Lanczos method

no code implementations15 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

Fast Robust PCA on Graphs

no code implementations29 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.

Dimensionality Reduction

Geodesic convolutional neural networks on Riemannian manifolds

no code implementations26 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.

Functional correspondence by matrix completion

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.

Matrix Completion

Matrix Completion on Graphs

2 code implementations7 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 #13 on Recommendation Systems on MovieLens 100K (using extra training data)

Collaborative Filtering Matrix Completion +1

Learning Laplacian Matrix in Smooth Graph Signal Representations

2 code implementations30 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.

Graph Learning

UNLocBoX: A MATLAB convex optimization toolbox for proximal-splitting methods

no code implementations4 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.

A Compressed Sensing Framework for Magnetic Resonance Fingerprinting

no code implementations9 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

Robust image reconstruction from multi-view measurements

no code implementations13 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.

Image Reconstruction Super-Resolution

The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains

1 code implementation31 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.


Wavelets on Graphs via Spectral Graph Theory

1 code implementation19 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

Cannot find the paper you are looking for? You can Submit a new open access paper.