181 citations · 661 across the 28 of their papers we have counts for
35 papers
High Resolution Seismic Waveform Generation using Denoising Diffusion
Kadek Hendrawan Palgunadi, Andreas Bergmeister, Andrea Bosisio +5
Accurate prediction and synthesis of seismic waveforms are crucial for seismic-hazard assessment and earthquake-resistant infrastructure design. Existing prediction methods, such a…
From STEM-EDXS data to phase separation and quantification using physics-guided NMF
Adrien Teurtrie, Nathanaël Perraudin, Thomas Holvoet +4
We present the development of a new algorithm which combines state-of-the-art energy-dispersive X-ray (EDX) spectroscopy theory and a suitable machine learning formulation for the…
Efficient algorithms for regularized Poisson Non-negative Matrix Factorization
Nathanaël Perraudin, Adrien Teutrie, Cécile Hébert +1
We consider the problem of regularized Poisson Non-negative Matrix Factorization (NMF) problem, encompassing various regularization terms such as Lipschitz and relatively smooth fu…
Efficient and Scalable Graph Generation through Iterative Local Expansion
Andreas Bergmeister, Karolis Martinkus, Nathanaël Perraudin +1
In the realm of generative models for graphs, extensive research has been conducted. However, most existing methods struggle with large graphs due to the complexity of representing…
An evaluation of deep learning models for predicting water depth evolution in urban floods
Stefania Russo, Nathanaël Perraudin, Steven Stalder +4
In this technical report we compare different deep learning models for prediction of water depth rasters at high spatial resolution. Efficient, accurate, and fast methods for water…
Diffusion Models for Graphs Benefit From Discrete State Spaces
Kilian Konstantin Haefeli, Karolis Martinkus, Nathanaël Perraudin +1
Denoising diffusion probabilistic models and score-matching models have proven to be very powerful for generative tasks. While these approaches have also been applied to the genera…
What You See is What You Classify: Black Box Attributions
Steven Stalder, Nathanaël Perraudin, Radhakrishna Achanta +2
An important step towards explaining deep image classifiers lies in the identification of image regions that contribute to individual class scores in the model's output. However, d…
SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators
Karolis Martinkus, Andreas Loukas, Nathanaël Perraudin +1
We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these…
A data acquisition setup for data driven acoustic design
Romana Rust, Achilleas Xydis, Kurt Heutschi +8
In this paper, we present a novel interdisciplinary approach to study the relationship between diffusive surface structures and their acoustic performance. Using computational desi…
DeepSphere: a graph-based spherical CNN
Michaël Defferrard, Martino Milani, Frédérick Gusset +1
Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representati…
Scalable Graph Networks for Particle Simulations
Karolis Martinkus, Aurelien Lucchi, Nathanaël Perraudin
Learning system dynamics directly from observations is a promising direction in machine learning due to its potential to significantly enhance our ability to understand physical sy…
GACELA -- A generative adversarial context encoder for long audio inpainting
Andres Marafioti, Piotr Majdak, Nicki Holighaus +1
We introduce GACELA, a generative adversarial network (GAN) designed to restore missing musical audio data with a duration ranging between hundreds of milliseconds to a few seconds…
Cosmological N-body simulations: a challenge for scalable generative models
Nathanaël Perraudin, Ankit Srivastava, Aurelien Lucchi +3
Deep generative models, such as Generative Adversarial Networks (GANs) or Variational Autoencoders (VAs) have been demonstrated to produce images of high visual quality. However, t…
Discriminative structural graph classification
Younjoo Seo, Andreas Loukas, Nathanaël Perraudin
This paper focuses on the discrimination capacity of aggregation functions: these are the permutation invariant functions used by graph neural networks to combine the features of n…
DeepSphere: towards an equivariant graph-based spherical CNN
Michaël Defferrard, Nathanaël Perraudin, Tomasz Kacprzak +1
Spherical data is found in many applications. By modeling the discretized sphere as a graph, we can accommodate non-uniformly distributed, partial, and changing samplings. Moreover…
Adversarial Generation of Time-Frequency Features with application in audio synthesis
Andrés Marafioti, Nicki Holighaus, Nathanaël Perraudin +1
Time-frequency (TF) representations provide powerful and intuitive features for the analysis of time series such as audio. But still, generative modeling of audio in the TF domain…
A domain agnostic measure for monitoring and evaluating GANs
Paulina Grnarova, Kfir Y Levy, Aurelien Lucchi +4
Generative Adversarial Networks (GANs) have shown remarkable results in modeling complex distributions, but their evaluation remains an unsettled issue. Evaluations are essential f…
DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
Nathanaël Perraudin, Michaël Defferrard, Tomasz Kacprzak +1
Convolutional Neural Networks (CNNs) are a cornerstone of the Deep Learning toolbox and have led to many breakthroughs in Artificial Intelligence. These networks have mostly been d…
Audio inpainting of music by means of neural networks
Andrés Marafioti, Nicki Holighaus, Piotr Majdak +1
We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps i…
Forecasting Time Series with VARMA Recursions on Graphs
Elvin Isufi, Andreas Loukas, Nathanael Perraudin +1
Graph-based techniques emerged as a choice to deal with the dimensionality issues in modeling multivariate time series. However, there is yet no complete understanding of how the u…
Improving DNN-based Music Source Separation using Phase Features
Joachim Muth, Stefan Uhlich, Nathanael Perraudin +3
Music source separation with deep neural networks typically relies only on amplitude features. In this paper we show that additional phase features can improve the separation perfo…
Large Scale Graph Learning from Smooth Signals
Vassilis Kalofolias, Nathanaël Perraudin
Graphs are a prevalent tool in data science, as they model the inherent structure of the data. They have been used successfully in unsupervised and semi-supervised learning. Typica…
A Time-Vertex Signal Processing Framework
Francesco Grassi, Andreas Loukas, Nathanaël Perraudin +1
An emerging way to deal with high-dimensional non-euclidean data is to assume that the underlying structure can be captured by a graph. Recently, ideas have begun to emerge related…
Compressive Embedding and Visualization using Graphs
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 refere…