Cross Project Defect Prediction via Balanced Distribution Adaptation Based Transfer Learning

作     者：Zhou Xu Shuai Pang Tao Zhang Xia-Pu Luo Jin Liu Yu-Tian Tang Xiao Yu Lei Xue 

作者机构：College of Computer Science and TechnologyHarbin Engineering UniversityHarbin 150001China School of Computer ScienceWuhan UniversityWuhan 430072China Department of ComputingThe Hong Kong Polytechnic UniversityHong Kong 999077China Department of ComputingThe Hong Kong Polytechnic UniversityHong Kong 999077China Key Laboratory of Network Assessment TechnologyInstitute of Information EngineeringChinese Academy of Sciences Beijing 100190China Guangxi Key Laboratory of Trusted SoftwareGuilin University of Electronic TechnologyGuilin 541004China Department of Computer ScienceCity University of Hong KongHong Kong 999077China 

出 版 物：《Journal of Computer Science & Technology》 (计算机科学技术学报（英文版）)

年 卷 期：2019年第34卷第5期

页      面：1039-1062页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：partially supported by the National Key Research and Development Program of China under Grant No.2018YFC1604000 the National Natural Science Foundation of China under Grant Nos. 61602258,61572374,and U163620068 the China Postdoctoral Science Foundation under Grant No. 2017M621247 the Natural Science Foundation of Heilongjiang Province of China under Grant No.LH2019F008,Heilongjiang Postdoctoral Science Foundation under Grant No.LBH-Z17047 the Open Fund of Key Laboratory of Network Assessment Technology from Chinese Academy of Sciences,Guangxi Key Laboratory of Trusted Software under Grant No. kx201607 the Academic Team Building Plan for Young Scholars from Wuhan University under Grant No. WHU2016012, Hong Kong GRC (Research Grants Council) Project under Grant Nos. PolyU 152223/17E and PolyU 152239/18E 

主　　题：cross-project defect prediction transfer learning balancing distribution effort-aware indicator 

摘      要：Defect prediction assists the rational allocation of testing resources by detecting the potentially defective software modules before releasing products. When a project has no historical labeled defect data, cross project defect prediction (CPDP) is an alternative technique for this scenario. CPDP utilizes labeled defect data of an external project to construct a classification model to predict the module labels of the current project. Transfer learning based CPDP methods are the current mainstream. In general, such methods aim to minimize the distribution differences between the data of the two projects. However, previous methods mainly focus on the marginal distribution difference but ignore the conditional distribution difference, which will lead to unsatisfactory performance. In this work, we use a novel balanced distribution adaptation (BDA) based transfer learning method to narrow this gap. BDA simultaneously considers the two kinds of distribution differences and adaptively assigns different weights to them. To evaluate the effectiveness of BDA for CPDP performance, we conduct experiments on 18 projects from four datasets using six indicators (i.e., F-measure, g-means, Balance, AUC, EARecall, and EAF-measure). Compared with 12 baseline methods, BDA achieves average improvements of 23.8%, 12.5%, 11.5%, 4.7%, 34.2%, and 33.7% in terms of the six indicators respectively over four datasets.