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:20250626T233526Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241120T100000
DTEND;TZID=America/New_York:20241120T170000
UID:submissions.supercomputing.org_SC24_sess533_post275@linklings.com
SUMMARY:A Sparse Approach for Translation-Based Training of Knowledge Grap
 h Embeddings
DESCRIPTION:Md Saidul Hoque Anik and Ariful Azad (Indiana University)\n\nK
 nowledge graph (KG) learning offers a powerful framework for generating ne
 w knowledge and making inferences. Training KG embedding can take a signif
 icantly long time, especially for larger datasets. Our analysis shows that
  the gradient computation of embedding and vector normalization are the do
 minant functions in the KG embedding training loop. We address this issue 
 by replacing the core embedding computation with SpMM (Sparse-Dense Matrix
  Multiplication) kernels. This allows us to unify multiple scatter (and ga
 ther) operations as a single operation, reducing training time and memory 
 usage. Applying this sparse approach in training the TransE model results 
 in up to 5.7x speedup on the CPU and up to 1.7x speedup on the GPU. Distri
 buting this algorithm on 64 GPUs, we observe up to 3.9x overall speedup in
  each epoch. Our proposed sparse approach can also be extended to accelera
 te other translation-based models such as TransR and TransH.\n\nRegistrati
 on Category: Tech Program Reg Pass, Exhibits Reg Pass\n\nSession Chairs: A
 yesha Afzal (Friedrich-Alexander University, Erlangen-Nuremberg; Erlangen 
 National High Performance Computing Center); Sally Ellingson (University o
 f Kentucky); and Alan Sussman (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR