BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T054759Z
LOCATION:230-231-232
DTSTART;TZID=America/Chicago:20211116T140000
DTEND;TZID=America/Chicago:20211116T143000
UID:submissions.supercomputing.org_SC21_sess172_pap469@linklings.com
SUMMARY:Parallel Construction of Module Networks
DESCRIPTION:Paper\n\nParallel Construction of Module Networks\n\nSrivastav
 a, Chockalingam, Aluru, Aluru\n\nModule networks (MoNets) are a parameter-
 sharing specialization of Bayesian networks that are used for reasoning ab
 out multidimensional entities with concerted interactions between groups o
 f variables. Construction of MoNets is compute-intensive, with sequential 
 methods requiring months for learning networks with a few thousand variabl
 es. In this paper, we present the first scalable distributed-memory parall
 el solution for constructing MoNets by parallelizing Lemon-Tree, a widely 
 used sequential software. We demonstrate the scalability of our parallel m
 ethod on a key application of MoNets – the construction of genome-scale ge
 ne regulatory networks. Using 4096 cores, our parallel implementation cons
 tructs regulatory networks for 5,716 and 18,373 genes of two model organis
 ms in 24 minutes and 4.2 hours, compared to an estimated 49 and 1561 days 
 using Lemon-Tree for generating exactly the same networks, respectively. O
 ur method is application-agnostic and broadly applicable to the learning o
 f high-dimensional MoNets for any of its wide array of applications.\n\nTa
 g: Reproducibility Badge, Machine Learning and Artificial Intelligence\n\n
 Registration Category: Tech Program Reg Pass\n\nAward Finalist: Best Repro
 ducibility Advancement Finalist\n\nReproducibility Badges: Artifact Availa
 ble, Artifact Functional, Results Reproduced
END:VEVENT
END:VCALENDAR