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 

机构地区：[1]College of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China [2]School of Computer Science,Wuhan University,Wuhan 430072,China [3]Department of Computing,The Hong Kong Polytechnic University,Hong Kong 999077,China Department of Computing,The Hong Kong Polytechnic University,Hong Kong 999077,China [4]Key Laboratory of Network Assessment Technology,Institute of Information Engineering,Chinese Academy of Sciences Beijing 100190,China [5]Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin 541004,China [6]Department of Computer Science,City University of Hong Kong,Hong Kong 999077,China

出　　处：《Journal of Computer Science & Technology》2019年第5期1039-1062,共24页计算机科学技术学报（英文版）

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.

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.

关 键 词：cross-project defect prediction transfer learning balancing DISTRIBUTION effort-aware INDICATOR 

分 类 号：TP[自动化与计算机技术]