We study the problem of designing models for machine learning tasks defined on sets. In
contrast to the traditional approach of operating on fixed dimensional vectors, we consider …

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 …

Deep Learning's recent successes have mostly relied on Convolutional Networks, which
exploit fundamental statistical properties of images, sounds and video data: the local …

We introduce a simple permutation equivariant layer for deep learning with set structure.
This type of layer, obtained by parameter-sharing, has a simple implementation and linear …

We generalize the scattering transform to graphs and consequently construct a
convolutional neural network on graphs. We show that under certain conditions, any feature …

Stability is a key aspect of data analysis. In many applications, the natural notion of stability
is geometric, as illustrated for example in computer vision. Scattering transforms construct …

Graph representation learning has many real-world applications, from self-driving LiDAR,
3D computer vision to drug repurposing, protein classification, social networks analysis. An …

Recent advances in automatic speaker verification (ASV) lead to an increased interest in
securing these systems for real-world applications. Malicious spoofing attempts against ASV …

The scattering transform is a multilayered wavelet-based architecture that acts as a model of
convolutional neural networks. Recently, several works have generalized the scattering …

In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders
(MGVAE), the first hierarchical generative model to learn and generate graphs in a …