BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240521T011635Z
UID:0625CE12-B9E4-491C-9A90-27EA86CE4E8F
DTSTART;TZID=America/New_York:20240520T190000
DTEND;TZID=America/New_York:20240520T200000
DESCRIPTION:Graphs are pervasive in various fields\, including social netwo
 rks\, biological interactomes\, transportation networks\, and more. Unders
 tanding these graphs through structured representations is crucial for gra
 sping their complex topologies and interdependencies\, which are vital for
  numerous applications within these domains. In recent years\, Graph Neura
 l Networks (GNNs) have attracted considerable attention and shown promisin
 g results in many graph learning tasks. Despite this progress\, learning l
 ong-range dependencies within graphs continues to be a significant challen
 ge. In this talk\, Dr. Ma will discuss their recent advancements in enhanc
 ing the expressive power of GNNs to capture long-range information in grap
 hs effectively\, addressing real-world challenges in diverse interdiscipli
 nary applications\, such as medical image\, brain network analysis\, socia
 l network mining\, and program analysis. She will also introduce innovativ
 e work in using graph machine learning for efficient workload partitioning
  in system optimization. This approach not only improves system performanc
 e but also supports the scalable distributed training of large-scale GNNs.
 \n\nJoin us for an enlightening session!\n\n[تحلیل شبکه های ا
 جتماعی (Social Network Analysis) — به زبان ساده و جا
 مع –  فرادرس - مجله‌]\n\nSpeaker(s): Guixiang Ma\, \n\nVir
 tual: https://events.vtools.ieee.org/m/417881
LOCATION:Virtual: https://events.vtools.ieee.org/m/417881
ORGANIZER:lifanghescut@gmail.com
SEQUENCE:40
SUMMARY:Empowering Graph Neural Networks for Long-Range Learning on Graphs
URL;VALUE=URI:https://events.vtools.ieee.org/m/417881
X-ALT-DESC:Description: <br /><p>Graphs are pervasive in various fields\, i
 ncluding social networks\, biological interactomes\, transportation networ
 ks\, and more. Understanding these graphs through structured representatio
 ns is crucial for grasping their complex topologies and interdependencies\
 , which are vital for numerous applications within these domains. In recen
 t years\, Graph Neural Networks (GNNs) have attracted considerable attenti
 on and shown promising results in many graph learning tasks. Despite this 
 progress\, learning long-range dependencies within graphs continues to be 
 a significant challenge. In this talk\, Dr. Ma will discuss their recent a
 dvancements in enhancing the expressive power of GNNs to capture long-rang
 e information in graphs effectively\, addressing real-world challenges in 
 diverse interdisciplinary applications\, such as medical image\, brain net
 work analysis\, social network mining\, and program analysis. She will als
 o introduce innovative work in using graph machine learning for efficient 
 workload partitioning in system optimization. This approach not only impro
 ves system performance but also supports the scalable distributed training
  of large-scale GNNs.</p>\n<p>Join us for an enlightening session!</p>\n<p
 ><img style="font-family: -apple-system\, BlinkMacSystemFont\, 'Segoe UI'\
 , Roboto\, Oxygen\, Ubuntu\, Cantarell\, 'Open Sans'\, 'Helvetica Neue'\, 
 sans-serif\;" src="https://blog.faradars.org/wp-content/uploads/2018/09/So
 cial-Network-Analysis-1.jpg" alt="تحلیل شبکه های اجتماع
 ی (Social Network Analysis) &mdash\; به زبان ساده و جامع &
 ndash\;  فرادرس - مجله&zwnj\;" width="719" height="410"></p>
END:VEVENT
END:VCALENDAR