BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160558Z
LOCATION:Poster Module
DTSTART;TZID=America/New_York:20201118T083000
DTEND;TZID=America/New_York:20201118T170000
UID:submissions.supercomputing.org_SC20_sess340_spostu111@linklings.com
SUMMARY:Enhancing IoT Anomaly Detection Performance for Federated Learning
DESCRIPTION:ACM Student Research Competition: Graduate Poster, ACM Student
  Research Competition: Undergraduate Poster, Posters\n\nEnhancing IoT Anom
 aly Detection Performance for Federated Learning\n\nWeinger\n\nWhile feder
 ated learning has gained great attention for mobile computing with the ben
 efits of scalable cooperative learning and privacy protection capabilities
 , there still exist a great deal of technical challenges to make it practi
 cally deployable. For instance, distribution of the training process to a 
 myriad of devices limits the classification performance of deep neural net
 works, often showing significantly degraded metrics compared to centralize
 d learning. We propose that data augmentation can be used to ensure that c
 lient nodes have a sufficiently balanced set of examples for each class an
 d will contribute more optimal updates to the global model. We show experi
 mental results that employ statistical data generation techniques includin
 g random sampling and k-nearest neighbor algorithms. Our results indicate 
 that random sampling of minority class data yields significant improvement
 s for our IoT anomaly detection use case with manageable learning complexi
 ty.\n\nTag: Student Program\n\nRegistration Category: Tech Program Reg Pas
 s, Exhibits Reg Pass
END:VEVENT
END:VCALENDAR