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

Cross-Project Defect Prediction (CPDP), which borrows data from similarprojects by combining a transfer learner with a classifier, have emerged as apromising way to predict software defects when the available data about thetarget project is insufficient. How-ever, developing such a model is challengebecause it is difficult to determine the right combination of transfer learnerand classifier along with their optimal hyper-parameter settings. In thispaper, we propose a tool, dubbedBiLO-CPDP, which is the first of its kind toformulate the automated CPDP model discovery from the perspective of bi-levelprogramming. In particular, the bi-level programming proceeds the optimizationwith two nested levels in a hierarchical manner. Specifically, the upper-leveloptimization routine is designed to search for the right combination oftransfer learner and classifier while the nested lower-level optimizationroutine aims to optimize the corresponding hyper-parameter settings.ToevaluateBiLO-CPDP, we conduct experiments on 20 projects to compare it with atotal of 21 existing CPDP techniques, along with its single-level optimizationvariant and Auto-Sklearn, a state-of-the-art automated machine learning tool.Empirical results show that BiLO-CPDP champions better prediction performancethan all other 21 existing CPDP techniques on 70% of the projects, while be-ingoverwhelmingly superior to Auto-Sklearn and its single-level optimizationvariant on all cases. Furthermore, the unique bi-level formalizationinBiLO-CPDP also permits to allocate more budget to the upper-level, whichsignificantly boosts the performance.

BiLO-CPDP: Bi-Level Programming for Automated Model Discovery in Cross-Project Defect Prediction