LogLSHD: Fast Log Parsing with Locality-Sensitive Hashing and Dynamic Time Warping
Large-scale software systems generate vast volumes of system logs that are essential for monitoring, diagnosing, and performance optimization. However, the unstructured nature and ever-growing scale of these logs present significant challenges for manual analysis and automated downstream tasks such as anomaly detection. Log parsing addresses these challenges by converting raw logs into structured formats, enabling efficient log analysis. Despite its importance, existing log parsing methods suffer from limitations in efficiency and scalability, due to the large size of log data and their heterogeneous formats. To overcome these challenges, this study proposes a log parsing approach, LogLSHD, which leverages Locality-Sensitive Hashing (LSH) to group similar logs and integrates Dynamic Time Warping (DTW) to enhance the accuracy of template extraction. LogLSHD demonstrates exceptional efficiency in parsing time, significantly outperforming state-of-the-art methods. For example, compared to Drain, LogLSHD reduces the parsing time by 73% while increasing the parsing accuracy by 15%.
Thu 26 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
11:00 - 13:00 | |||
11:00 5mDay opening | Opening PROMISE 2025 | ||
11:06 59mKeynote | Keynote 1 (Dr. Jacques Klein) PROMISE 2025 Jacques Klein University of Luxembourg | ||
12:06 14mTalk | LO2: Microservice API Anomaly Dataset of Logs and Metrics PROMISE 2025 Alexander Bakhtin University of Oulu, Jesse Nyyssölä University of Helsinki, Yuqing Wang University of Helsinki, Finland, Noman Ahmad University of Oulu, Ke Ping University of Helsinki, Matteo Esposito University of Oulu, Mika Mäntylä University of Helsinki and University of Oulu, Davide Taibi University of Oulu | ||
12:21 14mTalk | LogLSHD: Fast Log Parsing with Locality-Sensitive Hashing and Dynamic Time Warping PROMISE 2025 Shu-Wei Huang Polytechnique Montréal, Xingfang Wu Polytechnique Montréal, Heng Li Polytechnique Montréal | ||
12:36 14mTalk | Leveraging LLMs for User Stories in AI Systems: UStAI Dataset PROMISE 2025 Asma Yamani King Fahd University of Petroleum and Minerals, Malak Baslyman King Fahd University of Petroleum & Minerals, Moataz Ahmed King Fahd University of Petroleum and Minerals |
Vega is close to the registration desk.
Facing the registration desk, its entrance is on the left, close to the hotel side entrance.