Cross-company defect prediction via semi-supervised clustering-based data filtering and MSTrA-based transfer learning

Yu, Xiao; Wu, Man; Jian, Yiheng; Bennin, Kwabena Ebo; Fu, Mandi; Ma, Cuiluan

doi:10.1007/s00500-018-3093-1

Cited by 42 publications

(25 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve the shortage of labeled data, a feasible solution is making use of the information of both labeled and unlabeled software instances, and SSDP methods have been presented [33], [44]- [46]. Seliya and Khoshgoftaar [47] proposed an expectation maximization based semi-supervised method.…”

Section: B Semi-supervised Defect Prediction (Ssdp)mentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Learning for Cross-Project Semi-Supervised Defect Prediction

Sun

Jing

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Cross-project defect prediction (CPDP) aims to build a prediction model on existing source projects and predict the labels of target project. The data distribution difference between different projects makes CPDP very challenging. Besides, most existing CPDP methods usually require sufficient and labeled data. However, acquiring lots of labeled data for a new project is difficult while obtaining the unlabeled data is relatively easy. A desirable approach is building a prediction model on unlabeled data and labeled data. CPDP in this scenario is called cross-project semi-supervised defect prediction (CSDP). Recently, generative adversarial networks have achieved impressive results with these strong ability of learning data distribution and discriminative representation. For effectively learning the discriminative features of data from different projects, we propose a Discriminative Adversarial Feature Learning (DAFL) approach for CSDP. DAFL consists of feature transformer and project discriminator, which compete with each other. A feature transformer tries to generate feature representation, which learns the discriminant information and preserves intrinsic structure inferred from both labeled and unlabeled data. A project discriminator tries to discriminate source and target instances on the generated representation. Experiments on 16 projects show that DAFL performs significantly better than baselines. INDEX TERMS Cross-project defect prediction, adversarial learning, semi-supervised learning.

show abstract

Section: B Semi-supervised Defect Prediction (Ssdp)mentioning

confidence: 99%

“…Based on the relationship graph, NSGLP employs a label propagation algorithm to predict defectproneness of unlabeled instances. Yu et al [46] proposed a semi-supervised clustering-based data filtering (MsTrA+) method to filter out irrelevant cross-company data.…”

Section: B Semi-supervised Defect Prediction (Ssdp)mentioning

confidence: 99%

Adversarial Learning for Cross-Project Semi-Supervised Defect Prediction

Sun

Jing

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Ryu et al [12] proposed a transfer cost-sensitive boosting approach (TCSBoost) for CPDP with few labeled target data. Yu et al [31] proposed an effective solution for Cross-company defect prediction. They firstly provided a novel semi-supervised clustering-based data filtering approach to filter out irrelevant cross-company instances.…”

Section: Cpdp Approachesmentioning

confidence: 99%

Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction

Gong

Jiang

et al. 2019

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Heterogeneous defect prediction (HDP) is to detect the largest number of defective software modules in one project by using historical data collected from other projects with different metrics. However, these data can not be directly used because of different metrics set among projects. Meanwhile, software data have more non-defective instances than defective instances which may cause a significant bias towards defective instances. To completely solve these two restrictions, we propose unsupervised deep domain adaptation approach to build a HDP model. Specifically, we firstly map the data of source and target projects into a unified metric representation (UMR). Then, we design a simple neural network (SNN) model to deal with the heterogeneous and class-imbalanced problems in software defect prediction (SDP). In particular, our model introduces the Maximum Mean Discrepancy (MMD) as the distance between the source and target data to reduce the distribution mismatch, and use the cross-entropy loss function as the classification loss. Extensive experiments on 18 public projects from four datasets indicate that the proposed approach can build an effective prediction model for heterogeneous defect prediction (HDP) and outperforms the related competing approaches.

show abstract

“…(1) Although the 31 datasets in our experiment have been widely used in many software defect prediction studies, we still cannot claim that our conclusion can be generalized to other datasets. (2) We only study the seven regression algorithms without additional optimization for a given dataset. 3We only employ FPA as the evaluation measure.…”

Section: Threats To Validitymentioning

confidence: 99%

“…Therefore, defect prediction is often used to help to reasonably allocate limited development and maintenance resources [1]. So far, many efficient software defect prediction methods using statistical methods or machine learning techniques have been proposed [2][3][4], but they are usually confined to predicting a given software module being faulty or non-faulty by means of some binary classification techniques. 1 However, predicting the defect-prone of a given software module does not provide enough logistics to software testing in practice [5][6].…”

Section: Introductionmentioning

confidence: 99%

Revisting the Impact of Regression Models for Predicting the Number of Defects

Wu¹,

Ye²,

Li³

et al. 2018

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Predicting the number of faults in software modules can be more helpful instead of predicting the modules being faulty or non-faulty. Chen et al. (SEKE 397-402, 2015) and Rathore et al. (Soft Computing 21: 7417-7434, 2017) empirically investigate the feasibility of some regression algorithms for predicting the number of defects. The experimental results showed that the decision tree regression algorithm performed best in terms of average absolute error (AAE), average relative error (ARE) and root mean square error (RMSE). However, they did not consider the imbalanced data distribution problem in defect datasets and employed improper performance measures for evaluating the regression models to evaluate the performance of models for predicting the number of defects. Hence, we revisit the impact of different regression algorithms for predicting the number of defects using Fault-Percentile-Average (FPA) as the performance measure. The experiments on 31 datasets from PROMISE repository show that the prediction performance of models for predicting the number of defects built by different regression algorithms are various, and the gradient boosting regression algorithm and the Bayesian ridge regression algorithm can achieve better performance．

show abstract

Cross-company defect prediction via semi-supervised clustering-based data filtering and MSTrA-based transfer learning

Cited by 42 publications

References 41 publications

Adversarial Learning for Cross-Project Semi-Supervised Defect Prediction

Adversarial Learning for Cross-Project Semi-Supervised Defect Prediction

Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction

Revisting the Impact of Regression Models for Predicting the Number of Defects

Contact Info

Product

Resources

About