Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- M. Defferrard, X. Bresson, P. Vandergheynst
- Computer ScienceNIPS
- 30 June 2016
This work presents a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs.
Structured Sequence Modeling with Graph Convolutional Recurrent Networks
- Youngjoo Seo, M. Defferrard, P. Vandergheynst, X. Bresson
- Computer ScienceInternational Conference on Neural Information…
- 22 December 2016
The proposed model combines convolutional neural networks on graphs to identify spatial structures and RNN to find dynamic patterns in data structured by an arbitrary graph.
FMA: A Dataset for Music Analysis
- M. Defferrard, Kirell Benzi, P. Vandergheynst, X. Bresson
- Computer ScienceInternational Society for Music Information…
- 6 December 2016
The Free Music Archive is introduced, an open and easily accessible dataset suitable for evaluating several tasks in MIR, a field concerned with browsing, searching, and organizing large music collections, and some suitable MIR tasks are discussed.
DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
- Nathanael Perraudin, M. Defferrard, T. Kacprzak, R. Sgier
- Computer ScienceAstronomy and Computing
- 29 October 2018
Simplicial Neural Networks
- Stefania Ebli, M. Defferrard, Gard Spreemann
- Computer Science, MathematicsArXiv
- 7 October 2020
The SNNs are presented, a generalization of graph neural networks to data that live on a class of topological spaces called simplicial complexes, and an appropriate notion of convolution is defined that is leverage to construct the desired convolutional neural networks.
DeepSphere: a graph-based spherical CNN
- M. Defferrard, Martino Milani, Frédérick Gusset, Nathanael Perraudin
- PhysicsInternational Conference on Learning…
- 30 April 2020
DeepSphere, a method based on a graph representation of the discretized sphere, strikes a controllable balance between efficiency and rotation equivariance and suggests that anisotropic filters might be an unnecessary price to pay.
Connectome spectral analysis to track EEG task dynamics on a subsecond scale
- K. Glomb, Joan Rué Queralt, P. Hagmann
- Computer ScienceNeuroImage
- 23 June 2020
Learning to Recognize Musical Genre from Audio: Challenge Overview
- M. Defferrard, S. Mohanty, Sean F. Carroll, M. Salathé
- Computer ScienceThe Web Conference
- 23 April 2018
The authors here summarize the experience running a challenge with open data for musical genre recognition with some statistics about the submissions, and present the results.
RosettaSurf—A surface-centric computational design approach
- A. Scheck, S. Rosset, B. Correia
- BiologybioRxiv
- 16 June 2021
The RosettaSurf protocol combines the explicit optimization of molecular surface features with a global scoring function during the sequence design process, diverging from the typical design approaches that rely solely on an energy scoring function.
DeepSphere: towards an equivariant graph-based spherical CNN
- M. Defferrard, Nathanael Perraudin, T. Kacprzak, R. Sgier
- Computer ScienceArXiv
- 8 April 2019
This work discusses how to approach rotation equivariance using the graph neural network introduced in Defferrard et al. (2016), and shows good performance on rotation-invariant learning problems.
...
...