Search Results for author:
Found 21 papers, 12 papers with code
Efficient and Scalable Graph Generation through Iterative Local Expansion
However, most existing methods struggle with large graphs due to the complexity of representing the entire joint distribution across all node pairs and capturing both global and local graph structures simultaneously.
An evaluation of deep learning models for predicting water depth evolution in urban floods
In this technical report we compare different deep learning models for prediction of water depth rasters at high spatial resolution.
Diffusion Models for Graphs Benefit From Discrete State Spaces
Denoising diffusion probabilistic models and score-matching models have proven to be very powerful for generative tasks.
What You See is What You Classify: Black Box Attributions
These attributions are provided in the form of masks that only show the classifier-relevant parts of an image, masking out the rest.
SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators
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 eigenvalues and eigenvectors.
A data acquisition setup for data driven acoustic design
In this paper, we present the automated data acquisition setup, the data processing and the computational generation of diffusive surface structures.
DeepSphere: a graph-based spherical CNN
DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these two desiderata.
Scalable Graph Networks for Particle Simulations
However, the dynamics of many real-world systems are challenging to learn due to the presence of nonlinear potentials and a number of interactions that scales quadratically with the number of particles $N$, as in the case of the N-body problem.
GACELA -- A generative adversarial context encoder for long audio inpainting
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, i. e., to perform long-gap audio inpainting.
Emulation of cosmological mass maps with conditional generative adversarial networks
Weak gravitational lensing mass maps play a crucial role in understanding the evolution of structures in the universe and our ability to constrain cosmological models.
Cosmological N-body simulations: a challenge for scalable generative models
Our results show that the proposed model produces samples of high visual quality, although the statistical analysis reveals that capturing rare features in the data poses significant problems for the generative models.
Discriminative structural graph classification
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 nodes.
DeepSphere: towards an equivariant graph-based spherical CNN
Spherical data is found in many applications.
Adversarial Generation of Time-Frequency Features with application in audio synthesis
We demonstrate the potential of deliberate generative TF modeling by training a generative adversarial network (GAN) on short-time Fourier features.
DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
We present a spherical CNN for analysis of full and partial HEALPix maps, which we call DeepSphere.
Audio inpainting of music by means of neural networks
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.
Large Scale Graph Learning from Smooth Signals
In this paper, we show how to scale it, obtaining an approximation with leading cost of $\mathcal{O}(n\log(n))$, with quality that approaches the exact graph learning model.
A Time-Vertex Signal Processing Framework
An emerging way to deal with high-dimensional non-euclidean data is to assume that the underlying structure can be captured by a graph.
Compressive Embedding and Visualization using Graphs
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).
Stationary time-vertex signal processing
This paper considers regression tasks involving high-dimensional multivariate processes whose structure is dependent on some {known} graph topology.
Stationary signal processing on graphs
Graphs are a central tool in machine learning and information processing as they allow to conveniently capture the structure of complex datasets.
