BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Learning from the Interconnected World with Graphs
DTSTART:20230330T100000
DTEND:20230330T110000
DTSTAMP:20260407T152639Z
UID:3c18547bdbf72a42ab47a45e2cbcc65a641e8f0f295226b2595c25af
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Jiaxuan You - Stanford University\nIC Faculty candidate\n\
 nAbstract\nThe fact that our world is fundamentally interconnected present
 s unique challenges for modern data-driven research. In this talk\, I will
  present my research on investigating the interconnected world through the
  lens of graphs. Specifically\, I will present my research on accelerating
  graph AI research by systematically investigating the design space and ta
 sk space for graph deep learning. The research has democratized graph AI f
 or domain experts and helped them with scientific discoveries. Next\, I wi
 ll demonstrate my pioneering research in deep graph generative models whic
 h can generate novel realistic graph structures toward desirable objective
 s. This line of work has broad applications in molecule design and drug di
 scovery. Lastly\, I will show that graphs can further power AI problems in
  general domains. I will specifically cover my research in representing ne
 ural networks as relational graphs\, which advances the design and underst
 anding of deep neural networks and connects to network science and neurosc
 ience. Overall\, the talk will outline the promising path toward bridging 
 interdisciplinary research and extending the frontiers of AI with graphs.
  \n\nBio\nJiaxuan You received his CS Ph.D. from Stanford University\, ad
 vised by Prof. Jure Leskovec. His research investigates scientific and ind
 ustrial problems through the lens of graphs and develops graph AI methods 
 to solve these problems. He has published 12 first-author papers in NeurIP
 S\, ICML\, ICLR\, AAAI\, KDD\, and WWW\, many of which are widely recogniz
 ed. He has created or co-led multiple open-source software with over 20\,0
 00 combined GitHub stars. Jiaxuan has received multiple prestigious awards
 \, including a JPMorgan Chase Ph.D. Fellowship\, AAAI Best Student Paper A
 ward\, World Bank Best Big Data Solution\, and Outstanding TA Award from S
 tanford CS. He was the lead organizer of NeurIPS New Frontiers in Graph Le
 arning Workshop\, a co-organizer of the Stanford Graph Learning Workshop\,
  and a program committee member at numerous top-tier AI conferences and jo
 urnals. His Ph.D. research further leads to a startup Kumo AI which demons
 trates significant real-world impact.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420 https://epfl.zoom.us/
 j/67631618400
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR