Our Publications

Graph diffusion & PCA framework for semi-supervised learning

2021_By Inria & MyDataModels

A novel framework called Graph diffusion & PCA (GDPCA) is proposed in the context of semi-supervised learning on graph structured data. It combines a modified Principal Component Analysis with the classical supervised loss and Laplacian regularization, thus handling the case where the adjacency matrix is Sparse and avoiding the Curse of dimensionality.

GenPR: Generative PageRank Framework for Semi-supervised Learning on Citation Graphs

2020_By Inria & MyDataModels

Nowadays, Semi-Supervised Learning (SSL) on citation graph data sets is a rapidly growing area of research. However, the recently proposed graph-based SSL algorithms use a default adjacency matrix with binary weights on edges (citations), that causes a loss of the nodes (papers) similarity information.

2021 – PaZoe: Classifying time series with few labels

By Inria & MyDataModels

Semi-Supervised Learning (SSL) on graph-based datasets is a rapidly growing area of research, but its application to time series is difficult due to the time dimension.

2021 – Zoetrope Genetic Programming for Regression

By Inria & MyDataModels

The Zoetrope Genetic Programming (ZGP) algorithm is based on an original representation for mathematical expressions, targeting evolutionary symbolic regression.

2021 – ZGP : une alternative aux réseaux de neurones pour la segmentation sémantique de nuages dans les images satellites multi-spectrales

By IRT Saint Exupéry & MyDataModels

This paper presents the results of the evolutionary algorithm ZGP applied to cloud segmentation in remote sensing multispectral images. Many methods have been developed to automate cloud detection but can sometimes be difficult to implement on-board satellites.

2021 – In Space image processing using AI embedded on system on module: example of OPS-SAT cloud segmentation.

By Inria, Thalès, Elsys Design, IRT Saint Exupery & MyDataModels

This paper presents the in-flight results of different Artificial NeuralNetwork and an evolutionary algorithm as challenger, performing the inference of the large (4M-pixels) images on-board OPS-SAT (ESA Cubesat demostrator).