Write a Blog >>
ASE 2020
Mon 21 - Fri 25 September 2020 Melbourne, Australia
Wed 23 Sep 2020 09:30 - 09:50 at Wombat - AI for Software Engineering (3) Chair(s): Artur Andrzejak

Cross-Project Defect Prediction (CPDP), which borrows data from similar projects by combining a transfer learner with a classifier, have emerged as a promising way to predict software defects when the available data about the target project is insufficient. However, developing such a model is challenge because it is difficult to determine the right combination of transfer learner and classifier along with their optimal hyper-parameter settings. In this paper, we propose a tool, dubbed BiLO-CPDP, which is the first of its kind to formulate the automated CPDP model discovery from the perspective of bi-level programming. In particular, the bi-level programming proceeds the optimization with two nested levels in a hierarchical manner. Specifically, the upper-level optimization routine is designed to search for the right combination of transfer learner and classifier while the nested lower-level optimization routine aims to optimize the corresponding hyper-parameter settings. To evaluate BiLO-CPDP, we conduct experiments on 20 projects to compare it with a total of 21 existing CPDP techniques, along with its single-level optimization variant and Auto-Sklearn, a state-of-the-art automated machine learning tool. Empirical results show that BiLO-CPDP champions better prediction performance than all other 21 existing CPDP techniques on 70% of the projects, while being overwhelmingly superior to Auto-Sklearn and its single-level optimization variant on all cases. Furthermore, the unique bi-level formalization in BiLO-CPDP also permits to allocate more budget to the upper-level, which significantly boosts the performance.

Wed 23 Sep

Displayed time zone: (UTC) Coordinated Universal Time change

09:10 - 10:10
AI for Software Engineering (3)Research Papers at Wombat
Chair(s): Artur Andrzejak Heidelberg University
09:10
20m
Talk
Automatic Extraction of Cause-Effect-Relations from Requirements Artifacts
Research Papers
Julian Frattini Blekinge Institute of Technology, Maximilian Junker Technische Universit├Ąt Muenchen, Michael Unterkalmsteiner Blekinge Institute of Technology, Daniel Mendez Blekinge Institute of Technology
09:30
20m
Talk
BiLO-CPDP: Bi-Level Programming for Automated Model Discovery in Cross-Project Defect Prediction
Research Papers
Ke Li University of Exeter, Zilin Xiang University of Electronic Science and Technology of China, Tao Chen Loughborough University, Kay Chen Tan City University of Hong Kong
Pre-print
09:50
20m
Talk
Automating Just-In-Time Comment UpdatingACM Distinguished Paper
Research Papers
Zhongxin Liu Zhejiang University, Xin Xia Monash University, Meng Yan Chongqing University, Shanping Li Zhejiang University
Pre-print