RECORD
CSCLog: A Component Subsequence Correlation-Aware Log Anomaly Detection Method
Machine Learning · Submitted 7 Jul 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Extensive experiments on four publicly available log datasets demonstrate the effectiveness of CSCLog, outperforming the best baseline by an average of 7.41% in Macro F1-Measure.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Anomaly detection based on system logs plays an important role in intelligent operations, which is a challenging task due to the extremely complex log patterns. Existing methods detect anomalies by capturing the sequential dependencies in log sequences, which ignore the interactions of subsequences. To this end, we propose CSCLog, a Component Subsequence Correlation-Aware Log anomaly detection method, which not only captures the sequential dependencies in subsequences, but also models the implicit correlations of subsequences. Specifically, subsequences are extracted from log sequences based on components and the sequential dependencies in subsequences are captured by Long Short-Term Memory Networks (LSTMs). An implicit correlation encoder is introduced to model the implicit correlations of subsequences adaptively. In addition, Graph Convolution Networks (GCNs) are employed to accomplish the information interactions of subsequences. Finally, attention mechanisms are exploited to fuse the embeddings of all subsequences. Extensive experiments on four publicly available log datasets demonstrate the effectiveness of CSCLog, outperforming the best baseline by an average of 7.41% in Macro F1-Measure.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Anomaly detection based on system logs plays an important role in intelligent operations, which is a challenging task due to the extremely complex log patterns. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | Existing methods detect anomalies by capturing the sequential dependencies in log sequences, which ignore the interactions of subsequences. | gap 0.95 | 0.03 | 0.03 | asserted 1.00 |
| s2 | To this end, we propose CSCLog, a Component Subsequence Correlation-Aware Log anomaly detection method, which not only captures the sequential dependencies in subsequences, but also models the implicit correlations of subsequences. | contribution 1.00 | 0.90 | 0.18 | asserted 0.99 |
| s3 | Specifically, subsequences are extracted from log sequences based on components and the sequential dependencies in subsequences are captured by Long Short-Term Memory Networks (LSTMs). | method 1.00 | 0.84 | 0.02 | asserted 1.00 |
| s4 | An implicit correlation encoder is introduced to model the implicit correlations of subsequences adaptively. | method 0.97 | 0.87 | 0.03 | asserted 0.99 |
| s5 | In addition, Graph Convolution Networks (GCNs) are employed to accomplish the information interactions of subsequences. | method 1.00 | 0.81 | 0.02 | asserted 1.00 |
| s6 | Finally, attention mechanisms are exploited to fuse the embeddings of all subsequences. | method 1.00 | 0.84 | 0.03 | asserted 0.99 |
| s7 | Extensive experiments on four publicly available log datasets demonstrate the effectiveness of CSCLog, outperforming the best baseline by an average of 7.41% in Macro F1-Measure. | result 1.00 | 0.97 | 0.88 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Anomaly detection based on system logs plays an important role in intelligent operations, which is a challenging task due to the extremely complex log patterns. Existing methods detect anomalies by capturing the sequential dependencies in log sequences, which ignore the interactions of subsequences. To this end, we propose CSCLog, a Component Subsequence Correlation-Aware Log anomaly detection method, which not only captures the sequential dependencies in subsequences, but also models the implicit correlations of subsequences. Specifically, subsequences are extracted from log sequences based on components and the sequential dependencies in subsequences are captured by Long Short-Term Memory Networks (LSTMs). An implicit correlation encoder is introduced to model the implicit correlations of subsequences adaptively. In addition, Graph Convolution Networks (GCNs) are employed to accomplish the information interactions of subsequences. Finally, attention mechanisms are exploited to fuse the embeddings of all subsequences. Extensive experiments on four publicly available log datasets demonstrate the effectiveness of CSCLog, outperforming the best baseline by an average of 7.41% in Macro F1-Measure.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.