Edouard Pineau

A Simple Baseline Algorithm for Graph Classification

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

Using Laplacian Spectrum as Graph Feature Representation

Graphs possess exotic features like variable size and absence of natural ordering of the nodes that make them difficult to analyze and compare. To circumvent this problem and learn on graphs,...

Time Series Source Separation with Slow Flows

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...

InfoCatVAE: Representation Learning with Categorical Variational Autoencoders

This paper describes InfoCatVAE, an extension of the variational autoencoder that enables unsupervised disentangled representation learning. InfoCatVAE uses multimodal distributions for the prior...

Variational Recurrent Neural Networks for Graph Classification

We address the problem of graph classification based only on structural information. Inspired by natural language processing techniques (NLP), our model sequentially embeds information to estimate...

Seq2VAR: Multivariate Time Series Representation with Relational Neural Networks and Linear Autoregressive Model

Unsupervised ageing detection of mechanical systems on a causality graph

Universal hidden monotonic trend estimation with contrastive learning

In this paper, we describe a universal method for extracting the underlying monotonic trend factor from time series data. We propose an approach related to the Mann-Kendall test, a standard...