BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Unlocking Deep Learning for Graphs - Dominique Beaini\, Valence Di
 scovery\, MILA\, Canada
DTSTART:20210615T121500Z
DTEND:20210615T131500Z
UID:TALK160879@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:"Join us on Zoom":https://zoom.us/j/99166955895?pwd=SzI0M3pMVE
 kvNmw3Q0dqNDVRalZvdz09\n\nDeep learning has successfully transformed how w
 e tackle different problems\, especially in the fields of image/text recog
 nition and generation. However\, most methods remained constrained to thes
 e grid-like data structures and struggle to translate to more complex geom
 etries such as meshes and graphs. Having powerful deep learning on graphs 
 will unlock an unprecedented number of applications in different fields\, 
 such as social networks\, road navigation\, and drug discovery. In this ta
 lk\, I will discuss the main challenges of applying deep learning on graph
 s\, why early methods have struggled\, and how spectral theory is one of t
 he main keys in unlocking graph deep learning. Specifically\, I will discu
 ss some of our recent work including "Directional Graph Networks"\, which 
 offers the first generalization of convolutional neural networks to graphs
 \, and "Rethinking Graph Transformers with Spectral Attention"\, which off
 ers the first generalization of Transformers to graphs.\n\n*BIO:* \n\nDomi
 nique is the Head of Graph Research at "Valence Discovery"\, a startup loc
 ated at the Montreal Institute of Learning Algorithms (MILA). Our mission 
 focuses on unlocking deep learning for drug discovery via property predict
 ion\, screening\, and generation. We currently collaborate with multiple p
 harmaceutical companies and research laboratories to help them find better
  drugs\, faster\, cheaper\, and with fewer side effects.
LOCATION:Zoom
END:VEVENT
END:VCALENDAR