BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Improving the Aggregation in Graph Networks: can nodes understand 
 their neighbourhood? - Gabriele Corso
DTSTART:20201208T131500Z
DTEND:20201208T141500Z
UID:TALK154456@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:"Join us on Zoom":https://zoom.us/j/99166955895?pwd=SzI0M3pMVE
 kvNmw3Q0dqNDVRalZvdz09\n\nGraph Neural Networks have been shown to be effe
 ctive models for different predictive tasks on graph-structured data. This
  talk will combine the studies on the Principal Neighbourhood Aggregation 
 (NeurIPS 2020) and the Directional Graph Networks (oral at DiffGeo4DL work
 shop at NeurIPS 2020). We will examine the expressive power of graph neura
 l networks showing the limitations when it comes to the continuous feature
  spaces and directional kernels. Each of these will motivate improvements 
 to the aggregation method of GNNs which will lead us to fully generalize C
 NNs. Empirical results from molecular chemistry and computer vision benchm
 arks will validate our findings.
LOCATION:Zoom
END:VEVENT
END:VCALENDAR