28 citations · 60 across the 6 of their papers we have counts for
6 papers
Re-parameterizing VAEs for stability
David Dehaene, Rémy Brossard
We propose a theoretical approach towards the training numerical stability of Variational AutoEncoders (VAE). Our work is motivated by recent studies empowering VAEs to reach state…
Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining
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. GCE models are trai…
Realistic molecule optimization on a learned graph manifold
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. On the one hand, recent m…
Graph convolutions that can finally model local structure
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. This hin…
Anomaly localization by modeling perceptual features
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…
Iterative energy-based projection on a normal data manifold for anomaly localization
David Dehaene, Oriel Frigo, Sébastien Combrexelle +1
Autoencoder reconstructions are widely used for the task of unsupervised anomaly localization. Indeed, an autoencoder trained on normal data is expected to only be able to reconstr…