Universal hidden monotonic trend estimation with contrastive learning

no code implementations • 18 Oct 2022 • Edouard Pineau, Sébastien Razakarivony, Mauricio Gonzalez, Anthony Schrapffer

In this paper, we describe a universal method for extracting the underlying monotonic trend factor from time series data.

Contrastive Learning Time Series +1

Time Series Source Separation with Slow Flows

no code implementations • 20 Jul 2020 • Edouard Pineau, Sébastien Razakarivony, Thomas Bonald

In this paper, we show that slow feature analysis (SFA), a common time series decomposition method, naturally fits into the flow-based models (FBM) framework, a type of invertible neural latent variable models.

blind source separation Time Series +1

Using Laplacian Spectrum as Graph Feature Representation

3 code implementations • 2 Dec 2019 • Edouard Pineau

Graphs possess exotic features like variable size and absence of natural ordering of the nodes that make them difficult to analyze and compare.

Variational Recurrent Neural Networks for Graph Classification

1 code implementation • 7 Feb 2019 • Edouard Pineau, Nathan de Lara

We address the problem of graph classification based only on structural information.

General Classification Graph Classification

A Simple Baseline Algorithm for Graph Classification

3 code implementations • 22 Oct 2018 • Nathan de Lara, Edouard Pineau

Graph classification has recently received a lot of attention from various fields of machine learning e. g. kernel methods, sequential modeling or graph embedding.

BIG-bench Machine Learning General Classification +2

InfoCatVAE: Representation Learning with Categorical Variational Autoencoders

1 code implementation • 20 Jun 2018 • Edouard Pineau, Marc Lelarge

This paper describes InfoCatVAE, an extension of the variational autoencoder that enables unsupervised disentangled representation learning.

Clustering Representation Learning