CSCLog：一种组件子序列相关性感知的日志异常检测方法
CSCLog: A Component Subsequence Correlation-Aware Log Anomaly Detection Method
AI总结：
本文提出CSCLog日志异常检测方法，通过LSTM捕获组件子序列内顺序依赖，利用隐式相关性编码器和GCN建模子序列间隐式相关性与信息交互，并用注意力机制融合嵌入，在四个公开日志数据集上取得优于最佳基线平均7.41%的Macro F1-Measure提升。
摘要：
基于系统日志的异常检测在智能运维中发挥着重要作用，由于日志模式极其复杂，这是一项具有挑战性的任务。现有方法通过捕获日志序列中的顺序依赖关系来检测异常，但忽略了子序列之间的交互。为此，我们提出了CSCLog，一种组件子序列相关性感知的日志异常检测方法，它不仅捕获子序列中的顺序依赖关系，还对子序列的隐式相关性进行建模。具体来说，基于组件从日志序列中提取子序列，并通过长短期记忆网络（LSTMs）捕获子序列中的顺序依赖关系。引入隐式相关性编码器来自适应地建模子序列的隐式相关性。此外，采用图卷积网络（GCNs）完成子序列之间的信息交互。最后，利用注意力机制融合所有子序列的嵌入。在四个公开可用的日志数据集上的大量实验证明了CSCLog的有效性，在Macro F1-Measure上平均比最佳基线高出7.41%。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
