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:20230124T171521Z
LOCATION:C143-149
DTSTART;TZID=America/Chicago:20221114T143500
DTEND;TZID=America/Chicago:20221114T145900
UID:submissions.supercomputing.org_SC22_sess461_ws_ftxs105@linklings.com
SUMMARY:ClusterLog: Clustering Logs for Effective Log-Based Anomaly Detect
 ion
DESCRIPTION:Workshop\n\nClusterLog: Clustering Logs for Effective Log-Base
 d Anomaly Detection\n\nEgersdoerfer, Zhang, Dai\n\nWith the increasing pre
 valence of scalable file systems in the context of HPC, the importance of 
 accurate anomaly detection on runtime logs is increasing. But as it curren
 tly stands, many log-based anomaly detection methods have encountered nume
 rous challenges when applied to logs from many parallel file systems (PFSe
 s) due to their irregularity and ambiguity in time-based log sequences. To
  circumvent these problems, this study proposes ClusterLog, a log pre-proc
 essing method to cluster temporal sequence of log keys based on their sema
 ntic similarity. By grouping semantically and sentimentally similar logs, 
 it aims to represent log sequences with the smallest amount of unique log 
 keys, intending to improve the ability for a downstream sequence based mod
 el to learn the log patterns. The preliminary results indicate not only it
 s effectiveness in reducing the granularity of log sequences without the l
 oss of important sequence information, but also its generalizability to di
 fferent file systems’ logs.\n\nSession Format: Recorded\n\nRegistration Ca
 tegory: Workshop Reg Pass
END:VEVENT
END:VCALENDAR