BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:NeVAE: A Deep Generative Model for Molecular Graphs - Abir De\, Ma
 x Planck Institute for Software Systems
DTSTART:20190408T100000Z
DTEND:20190408T110000Z
UID:TALK122509@talks.cam.ac.uk
CONTACT:Robert Peharz
DESCRIPTION:Deep generative models have been praised for their ability to 
 learn smooth latent representation of images\, text\, and audio\, which ca
 n then be used to generate new\, plausible data. However\, current generat
 ive models are unable to work with molecular graphs due to their unique ch
 aracteristics--their underlying structure is not Euclidean or grid-like\, 
 they remain isomorphic under permutation of the node labels\, and they com
 e with a different number of nodes and edges. In this work\, we propose Ne
 VAE\, a novel variational autoencoder for molecular graphs\, whose encoder
  and decoder are specially designed to account for the above properties by
  means of several technical innovations. In addition\, by using masking\, 
 the decoder is able to guarantee a set of valid properties in the generate
 d molecules. Experiments reveal that our model can discover plausible\, di
 verse and novel molecules more effectively than several state of the art m
 ethods. Moreover\, by utilizing Bayesian optimization over the continuous 
 latent representation of molecules our model finds\, we can also find mole
 cules that maximize certain desirable properties more effectively than alt
 ernatives.
LOCATION:Engineering Department\, CBL Room BE-438.
END:VEVENT
END:VCALENDAR