English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Prompt and accurate detection of system anomalies is essential to ensure thereliability of software systems. Unlike manual efforts that exploit allavailable run-time information, existing approaches usually leverage only asingle type of monitoring data (often logs or metrics) or fail to makeeffective use of the joint information among different types of data.Consequently, many false predictions occur. To better understand themanifestations of system anomalies, we conduct a systematical study on a largeamount of heterogeneous data, i.e., logs and metrics. Our study demonstratesthat logs and metrics can manifest system anomalies collaboratively andcomplementarily, and neither of them only is sufficient. Thus, integratingheterogeneous data can help recover the complete picture of a system's healthstatus. In this context, we propose Hades, the first end-to-end semi-supervisedapproach to effectively identify system anomalies based on heterogeneous data.Our approach employs a hierarchical architecture to learn a globalrepresentation of the system status by fusing log semantics and metricpatterns. It captures discriminative features and meaningful interactions fromheterogeneous data via a cross-modal attention module, trained in asemi-supervised manner. We evaluate Hades extensively on large-scale simulateddata and datasets from Huawei Cloud. The experimental results present theeffectiveness of our model in detecting system anomalies. We also release thecode and the annotated dataset for replication and future research.

Heterogeneous Anomaly Detection for Software Systems via Semi-supervised Cross-modal Attention