BEGIN:VCALENDAR METHOD:REQUEST PRODID:Microsoft Exchange Server 2010 VERSION:2.0 BEGIN:VTIMEZONE TZID:UTC BEGIN:STANDARD DTSTART:16010101T000000 TZOFFSETFROM:+0000 TZOFFSETTO:+0000 END:STANDARD BEGIN:DAYLIGHT DTSTART:16010101T000000 TZOFFSETFROM:+0000 TZOFFSETTO:+0000 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT ORGANIZER;CN=Evgeny Osipov:mailto:evgeny.osipov@ltu.se ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN='Google Gr oups' via VSACommunity:mailto:vsacommunity@googlegroups.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Parikshit Ram:mailto:Parikshit.Ram@ibm.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Daswin De Silva:mailto:D.DeSilva@latrobe.edu.au ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Fredrick A ngelo Galapon:mailto:fredrick.galapon@eee.upd.edu.ph ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Cynamon, J osh":mailto:jcynamon@iu.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="MCDONALD, NATHAN R CIV USAF AFMC AFRL/RITB":mailto:nathan.mcdonald.5@us.af.mil ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Ibrahim, M ohamed":mailto:mibrahim@utdallas.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Ross Gayle r:mailto:r.gayler@gmail.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=GEETH R DE MEL:mailto:geeth.demel@uk.ibm.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Marco Angi oli:mailto:marco.angioli@uniroma1.it ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Peter Bruz a:mailto:p.bruza@qut.edu.au ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Colyn Seel ey:mailto:colynseeley218@gmail.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Jesper Ols en:mailto:jesper.olsen@gmail.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Wanyu Lei: mailto:wlei@berkeley.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Leonid Mok rushin:mailto:leonid.mokrushin@ericsson.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Rocco Mart ino:mailto:rocco.martino@uniroma1.it ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Trevor Coh en:mailto:treversec@gmail.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Dave Bende r:mailto:davecbender@gmail.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Dmitri Rac hkovskij:mailto:dar@infrm.kiev.ua ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Giacomo Ca mposampiero:mailto:Giacomo.Camposampiero1@ibm.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Fatemeh As garinejad:mailto:fasgarinejad@ucsd.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Paxon Frad y:mailto:paxon.frady@gmail.com ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=n2mills:ma ilto:n2mills@ltu.edu.au ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Sadrzadeh, Mehrnoosh":mailto:m.sadrzadeh@ucl.ac.uk ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Antonello Rosato:mailto:antonello.rosato@uniroma1.it ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Ilya Pavel iev:mailto:paveliei@tcd.ie ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Ye Tian:ma ilto:yet002@ucsd.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Tajana Ros ing:mailto:tajana@ucsd.edu DESCRIPTION;LANGUAGE=en-GB:Dear all\,\n Welcome to the next talk of Season 11 on VSAONLINE. Ye Tian\, UC San Diego\, USA will deliver a talk\n”Fede rated Hyperdimensional Computing: Comprehensive Analysis and Robust Commun ication”\nDate: October 20\, 2025\nTime: 20:00 GMT\nZoom: https://ltu-s e.zoom.us/j/65564790287\n\nWEB: https://bit.ly/vsaonline\nTitle: Federate d Hyperdimensional Computing: Comprehensive Analysis and Robust Communicat ion.\nAbstract: Federated learning is a distributed learning method by tr aining the model in locally multiple clients\, which has been used in nume rous fields. Current convolutional neural networks (CNN)-based federated l earning approaches face challenges from computational cost\, communication efficiency\, and robust communication. Recently\, Hyper Dimensional Compu ting (HDC) has been recognized as a promising technique to address these c hallenges. HDC encodes data as high-dimensional vectors and enables lightw eight training and communication through simple parallel vector operations . Several HDC-based federated learning methods have been proposed. Althoug h existing methods reduce computational efficiency and communication cost\ , they are difficult to handle complex learning tasks and are not robust t o unreliable wireless channels. In this work\, we innovatively introduce a synergetic federated learning framework\, FHDnn. With the complementary s trengths of CNN and HDC\, FHDnn can achieve optimal performance on complex image tasks while maintaining good computational and communication effici ency. Secondly\, we demonstrate in detail the convergence of using HDC in a generalized federated learning framework\, providing theoretical guarant ees for HDC-based federated learning approach. Finally\, we design three c ommunication strategies to further improve the communication efficiency of FHDnn by 32×. Experiments demonstrate that FHDnn converges 3× faster th an CNN-based federated learning methods\, reduces the communication cost b y 2\,112×\, and the local computation and energy consumption by 192×. In addition\, it has good robustness to unreliable communication with bit er rors\, noise\, and packet loss.\n UID:040000008200E00074C5B7101A82E00800000000794880C06D08DC01000000000000000 0100000003C52A1DB3A206D4881905B5B8FB19D51 SUMMARY;LANGUAGE=en-GB:VSAONLINE. SEASON 11. October 20\, 20:00GMT. Ye Tia n. DTSTART;TZID=UTC:20251020T200000 DTEND;TZID=UTC:20251020T210000 CLASS:PUBLIC PRIORITY:5 DTSTAMP:20251017T051416Z TRANSP:OPAQUE STATUS:CONFIRMED SEQUENCE:8 LOCATION;LANGUAGE=en-GB:https://ltu-se.zoom.us/j/65564790287 X-MICROSOFT-CDO-APPT-SEQUENCE:8 X-MICROSOFT-CDO-OWNERAPPTID:2123907757 X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY X-MICROSOFT-CDO-ALLDAYEVENT:FALSE X-MICROSOFT-CDO-IMPORTANCE:1 X-MICROSOFT-CDO-INSTTYPE:0 X-MICROSOFT-ONLINEMEETINGEXTERNALLINK: X-MICROSOFT-DONOTFORWARDMEETING:FALSE X-MICROSOFT-DISALLOW-COUNTER:FALSE X-MICROSOFT-REQUESTEDATTENDANCEMODE:DEFAULT X-MICROSOFT-ISRESPONSEREQUESTED:TRUE X-MICROSOFT-LOCATIONDISPLAYNAME:https://ltu-se.zoom.us/j/65564790287 X-MICROSOFT-LOCATIONSOURCE:None X-MICROSOFT-LOCATIONS:[{"DisplayName":"https://ltu-se.zoom.us/j/65564790287 "\,"LocationAnnotation":""\,"LocationUri":""\,"LocationStreet":""\,"Locati onCity":""\,"LocationState":""\,"LocationCountry":""\,"LocationPostalCode" :""\,"LocationFullAddress":""}] END:VEVENT END:VCALENDAR