Self-supervised learning holds promise to revolutionize molecule propert...
One of the main arguments behind studying disentangled representations i...
Modern generative models achieve excellent quality in a variety of tasks...
We propose FlowSVDD – a flow-based one-class classifier for anomaly/outl...
Graph neural networks have recently become a standard method for analysi...
We investigate the problem of training neural networks from incomplete i...
We propose OneFlow - a flow-based one-class classifier for anomaly (outl...
Designing a single neural network architecture that performs competitive...
Graph Convolutional Networks (GCNs) have recently become the primary cho...
Non-linear source separation is a challenging open problem with many
app...
Hypernetworks mechanism allows to generate and train neural networks (ta...
In this paper, we propose a simple, fast and easy to implement algorithm...
Designing a molecule with desired properties is one of the biggest chall...
We construct a general unified framework for learning representation of
...