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

Configuration tuning for large software systems is generally challenging dueto the complex configuration space and expensive performance evaluation. Mostexisting approaches follow a two-phase process, first learning aregression-based performance prediction model on available samples and thensearching for the configurations with satisfactory performance using thelearned model. Such regression-based models often suffer from the scarcity ofsamples due to the enormous time and resources required to run a large softwaresystem with a specific configuration. Moreover, previous studies have shownthat even a highly accurate regression-based model may fail to discern therelative merit between two configurations, whereas performance comparison isactually one fundamental strategy for configuration tuning. To address theseissues, this paper proposes CM-CASL, a Comparison-based performance Modelingapproach for software systems via Collaborative Active and SemisupervisedLearning. CM-CASL learns a classification model that compares the performanceof two given configurations, and enhances the samples through a collaborativelabeling process by both human experts and classifiers using an integration ofactive and semisupervised learning. Experimental results demonstrate thatCM-CASL outperforms two state-of-the-art performance modeling approaches interms of both classification accuracy and rank accuracy, and thus provides abetter performance model for the subsequent work of configuration tuning.

CM-CASL: Comparison-based Performance Modeling of Software Systems via Collaborative Active and Semisupervised Learning