no code implementations • 25 Jun 2021 • David Dehaene, Rémy Brossard
We propose a theoretical approach towards the training numerical stability of Variational AutoEncoders (VAE).
no code implementations • 18 Jun 2021 • Oriel Frigo, Rémy Brossard, David Dehaene
We propose the Graph Context Encoder (GCE), a simple but efficient approach for graph representation learning based on graph feature masking and reconstruction.
no code implementations • 3 Jun 2021 • Rémy Brossard, Oriel Frigo, David Dehaene
Deep learning based molecular graph generation and optimization has recently been attracting attention due to its great potential for de novo drug design.
1 code implementation • 30 Nov 2020 • Rémy Brossard, Oriel Frigo, David Dehaene
Despite quick progress in the last few years, recent studies have shown that modern graph neural networks can still fail at very simple tasks, like detecting small cycles.
Ranked #13 on Graph Property Prediction on ogbg-molpcba
1 code implementation • 12 Aug 2020 • David Dehaene, Pierre Eline
Although unsupervised generative modeling of an image dataset using a Variational AutoEncoder (VAE) has been used to detect anomalous images, or anomalous regions in images, recent works have shown that this method often identifies images or regions that do not concur with human perception, even questioning the usability of generative models for robust anomaly detection.
Ranked #18 on Anomaly Detection on VisA
1 code implementation • ICLR 2020 • David Dehaene, Oriel Frigo, Sébastien Combrexelle, Pierre Eline
Indeed, an autoencoder trained on normal data is expected to only be able to reconstruct normal features of the data, allowing the segmentation of anomalous pixels in an image via a simple comparison between the image and its autoencoder reconstruction.
Ranked #81 on Anomaly Detection on MVTec AD (Segmentation AUROC metric)