BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Yusu Wang (UC San Diego)
DTSTART:20240112T150000Z
DTEND:20240112T160000Z
DTSTAMP:20260423T022921Z
UID:GEOTOP-A/79
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GEOTOP-A/79/
 ">Graph learning models: theoretical understanding\, limitations and enhan
 cements</a>\nby Yusu Wang (UC San Diego) as part of GEOTOP-A seminar\n\n\n
 Abstract\nGraph data is ubiquitous in many application domains. The rapid 
 advancements in machine learning also lead to many new graph learning fram
 eworks\, such as message passing (graph) neural networks (MPNNs)\, graph t
 ransformers and higher order variants. In this talk\, I will describe some
  of our recent journey in attempting to provide better (theoretical) under
 standing of these graph learning models (e.g\, their representation power 
 and limitations in capturing long range interactions in graphs)\, the pros
  and cons of different models\, and ways to further enhance them in practi
 ce. This talk is based on multiple pieces of work with various collaborato
 rs\, whom I will mention in the talk.\n
LOCATION:https://researchseminars.org/talk/GEOTOP-A/79/
END:VEVENT
END:VCALENDAR