BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Australia/Brisbane
BEGIN:STANDARD
DTSTART:19920301T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261009T115118Z
UID:5F37498D-A67D-44E8-A66E-0250E7333C50
DTSTART;TZID=Australia/Brisbane:20261013T160000
DTEND;TZID=Australia/Brisbane:20261013T173000
DESCRIPTION:Abstract\n\nAs wireless networks become increasingly dense and 
 heterogeneous\, managing interference and allocating resources demand meth
 ods that can account for complex interactions among network entities. Grap
 h deep learning (GDL) provides a natural framework for learning from these
  interactions by incorporating network structure into neural architectures
 .\n\nThis talk introduces the principles of GDL and explains why the struc
 tural properties of graph neural networks\, including permutation equivari
 ance and local message passing\, make them well suited to wireless communi
 cation problems.\n\nDrawing on examples including space-air-ground integra
 ted networks and cell-free massive MIMO\, it illustrates how graph represe
 ntations can support resource allocation and network optimization\, includ
 ing through integration with deep reinforcement learning.\n\nThe talk conc
 ludes with open challenges in generalization\, distributed implementation\
 , and robustness under realistic wireless conditions\, highlighting opport
 unities for further research at the intersection of wireless communication
 s and machine learning.\n\nSpeaker Biography\n\nPeng Cheng is an Associate
  Professor in the Department of Computer Science and Information Technolog
 y at La Trobe University\, Australia.\n\nHis research interests include ma
 chine learning\, graph neural networks\, and their applications in wireles
 s communications and intelligent networks.\n\nCo-sponsored by: Center for 
 AI and Data Science Innovation (CADSI)\, James Cook University\n\nVirtual:
  https://events.vtools.ieee.org/m/583758
LOCATION:Virtual: https://events.vtools.ieee.org/m/583758
ORGANIZER:tao.huang1@jcu.edu.au
SEQUENCE:9
SUMMARY:Graph Deep Learning for Wireless Communications: Principles\, Appli
 cations\, and Open Challenges
URL;VALUE=URI:https://events.vtools.ieee.org/m/583758
X-ALT-DESC:Description: <br /><h2>Abstract</h2>\n<p>As wireless networks be
 come increasingly dense and heterogeneous\, managing interference and allo
 cating resources demand methods that can account for complex interactions 
 among network entities. Graph deep learning (GDL) provides a natural frame
 work for learning from these interactions by incorporating network structu
 re into neural architectures.</p>\n<p>This talk introduces the principles 
 of GDL and explains why the structural properties of graph neural networks
 \, including permutation equivariance and local message passing\, make the
 m well suited to wireless communication problems.</p>\n<p>Drawing on examp
 les including space-air-ground integrated networks and cell-free massive M
 IMO\, it illustrates how graph representations can support resource alloca
 tion and network optimization\, including through integration with deep re
 inforcement learning.</p>\n<p>The talk concludes with open challenges in g
 eneralization\, distributed implementation\, and robustness under realisti
 c wireless conditions\, highlighting opportunities for further research at
  the intersection of wireless communications and machine learning.</p>\n<h
 2>Speaker Biography</h2>\n<p>Peng Cheng is an Associate Professor in the D
 epartment of Computer Science and Information Technology at La Trobe Unive
 rsity\, Australia.</p>\n<p>His research interests include machine learning
 \, graph neural networks\, and their applications in wireless communicatio
 ns and intelligent networks.</p>
END:VEVENT
END:VCALENDAR