BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260402T024533Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20250623T180000
DTEND;TZID=America/Los_Angeles:20250623T190000
UID:dac_DAC 2025_sess262_RESEARCH2376@linklings.com
SUMMARY:CLEAR-HD: Computationally Light and Effective Unlearning for Hyper
 dimensional Computing
DESCRIPTION:Fatemeh Asgarinejad and Tajana Rosing (University of Californi
 a, Santa Barbara) and Baris Aksanli (San Diego State University)\n\nThe ab
 ility to selectively forget learned information--capability crucial for pr
 ivacy, security, and dynamic adaptation--is unexplored in Hyperdimensional
  computing (HDC) systems. In this paper, we show that unlearning in HDC is
  challenging due to its memorization nature, making it difficult to natura
 lly forget specific information. We then present CLEAR-HD, a light-weight 
 and effective framework for HDC unlearning. CLEAR-HD tracks the effect of 
 encoded vectors in the model and offsets the impact of unlearned data by a
 ppropriate substitutes. CLEAR-HD also utilizes a selective retraining to m
 inimize accuracy loss. CLEAR-HD outperforms the baselines in unlearning qu
 ality, accuracy, and performance.\n\nTracks: DES5: Emerging Device and Int
 erconnect Technologies\n\n
END:VEVENT
END:VCALENDAR