Write a Blog >>
ICSE 2021
Mon 17 May - Sat 5 June 2021

With the growth of software systems, logs have become an important data to aid system maintenance. Log-based anomaly detection is one of the most important methods for such purpose, which aims to automatically detect system anomalies via log analysis. However, existing log-based anomaly detection approaches still suffer from practical issues due to either depending on a large amount of manually labeled training data (supervised approaches) or unsatisfactory performance without learning the knowledge on historical anomalies (unsupervised and semi-supervised approaches). In this paper, we propose a novel practical log-based anomaly detection approach, PLELog, which is semi-supervised to get rid of time-consuming manual labeling and incorporates the knowledge on historical anomalies via probabilistic label estimation to bring supervised approaches’ superiority into play. In addition, PLELog is able to stay immune to unstable log data via semantic embedding and detect anomalies efficiently and effectively by designing an attention-based GRU neural network. We evaluated PLELog on two most widely-used public datasets, and the results demonstrate the effectiveness of PLELog, significantly outperforming the compared approaches with an average of 181.6% improvement in terms of F1-score. In particular, PLELog has been applied to two real-world systems from our university and a large corporation, further demonstrating its practicability.

Wed 26 May

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

14:30 - 15:25
14:30
20m
Paper
Semi-supervised Log-based Anomaly Detection via Probabilistic Label EstimationArtifact ReusableTechnical TrackArtifact Available
Technical Track
Lin Yang College of Intelligence and Computing, Tianjin University, Junjie Chen College of Intelligence and Computing, Tianjin University, Zan Wang College of Intelligence and Computing, Tianjin University, Weijing Wang College of Intelligence and Computing, Tianjin University, Jiajun Jiang College of Intelligence and Computing, Tianjin University, Xuyuan Dong Information and Network Center,Tianjin University, Wenbin Zhang Information and Network Center,Tianjin University
Pre-print Media Attached
14:50
20m
Paper
DeepLV: Suggesting Log Levels Using Ordinal Based Neural NetworksTechnical Track
Technical Track
Zhenhao Li Concordia University, Heng Li Polytechnique Montréal, Tse-Hsun (Peter) Chen Concordia University, Weiyi Shang Concordia University
Pre-print Media Attached
15:10
15m
Short-paper
On Automatic Parsing of Log RecordsNIER
NIER - New Ideas and Emerging Results
Jared Rand Ryerson University, Andriy Miranskyy Ryerson University
Pre-print Media Attached

Thu 27 May

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

02:30 - 03:25
02:30
20m
Paper
Semi-supervised Log-based Anomaly Detection via Probabilistic Label EstimationArtifact ReusableTechnical TrackArtifact Available
Technical Track
Lin Yang College of Intelligence and Computing, Tianjin University, Junjie Chen College of Intelligence and Computing, Tianjin University, Zan Wang College of Intelligence and Computing, Tianjin University, Weijing Wang College of Intelligence and Computing, Tianjin University, Jiajun Jiang College of Intelligence and Computing, Tianjin University, Xuyuan Dong Information and Network Center,Tianjin University, Wenbin Zhang Information and Network Center,Tianjin University
Pre-print Media Attached
02:50
20m
Paper
DeepLV: Suggesting Log Levels Using Ordinal Based Neural NetworksTechnical Track
Technical Track
Zhenhao Li Concordia University, Heng Li Polytechnique Montréal, Tse-Hsun (Peter) Chen Concordia University, Weiyi Shang Concordia University
Pre-print Media Attached
03:10
15m
Short-paper
On Automatic Parsing of Log RecordsNIER
NIER - New Ideas and Emerging Results
Jared Rand Ryerson University, Andriy Miranskyy Ryerson University
Pre-print Media Attached