• Home
  • Search
  • Feature Disentanglement Based Heterogeneous Defect Prediction
  • Cite Icon1
  • https://doi.org/10.1145/3742474Copy DOI Icon

Feature Disentanglement Based Heterogeneous Defect Prediction

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Cross-project defect prediction (CPDP) utilizes the existing labeled data in the source project to assist with the prediction of unlabeled projects in the target dataset, which effectively improves the prediction performance and has become a research hotspot in software engineering. At present, CPDP can be categorized into homogeneous cross-project defect prediction and heterogeneous cross-project defect prediction (HDP), in which HDP doesn’t require that the source project and the target project have the same feature space, thus, it is more widely used in the actual CPDP. Most of current HDP methods map the original features to the latent feature space and reduce the inter-project variation by transferring domain-independent features, but the transferring process ignores the use of domain-related features, which affects the prediction performance of the model. Moreover, the mapped latent features are not conducive to the model’s interpretability. Based on these, this paper proposes a heterogeneous defect prediction method based on feature disentanglement (FD-HDP). We disentangle the features using domain-related and domain-independent feature extractors, respectively, to improve the interpretability of the model by maximizing the domain adversarial loss during training and guiding the feature extractors to produce accurate domain-related and domain-independent features. The weighted sum of the prediction results from domain-related and domain-independent predictors is used as the final prediction result of the project during the prediction process, which realizes the combination of domain-independent and domain-related features and effectively improves the prediction performance. In this paper, we conducted experiments using four publicly available defect datasets to construct heterogeneous scenarios. The results demonstrate that the FD-HDP model shows significant advantages over state-of-the-art methods in six metrics.

Similar Papers
  • PDF
  • Research Article
  • Citations4

Multi-Source Heterogeneous Kernel Mapping in Software Defect Prediction

  • Apr 28, 2023
  • Applied Sciences
  • Jingxiu Yao +3
  • Research Article
  • Citations6

Joint Instance and Feature Adaptation for Heterogeneous Defect Prediction

  • Mar 01, 2024
  • IEEE Transactions on Reliability
  • Yujie Ren +2
  • Research Article
  • Citations51

Kernel Spectral Embedding Transfer Ensemble for Heterogeneous Defect Prediction

  • Jan 01, 2019
  • IEEE Transactions on Software Engineering
  • Haonan Tong +2
  • PDF
  • Research Article
  • Citations1

An optimized approach for class imbalance problem in heterogeneous cross project defect prediction

  • Sep 16, 2022
  • F1000Research
  • Lipika Goel +2
  • Research Article
  • Citations8

Heterogeneous cross-project defect prediction with multiple source projects based on transfer learning.

  • Nov 11, 2019
  • Mathematical Biosciences and Engineering
  • Xinglong Yin +3
  • Research Article
  • Citations127

Cost-sensitive transfer kernel canonical correlation analysis for heterogeneous defect prediction

  • Aug 16, 2017
  • Automated Software Engineering
  • Zhiqiang Li +5
  • Preprint Article

Moving from Cross-Project Defect Prediction to Heterogeneous Defect Prediction: A Partial Replication Study.

  • Mar 05, 2021
  • Hadi Jahanshahi +2
  • Conference Article
  • Citations193

Heterogeneous defect prediction

  • Aug 30, 2015
  • Jaechang Nam +1
  • Research Article
  • Citations62

An Empirical Study on Heterogeneous Defect Prediction Approaches

  • Jan 24, 2020
  • IEEE Transactions on Software Engineering
  • Haowen Chen +5
  • Research Article
  • Citations294

Heterogeneous Defect Prediction

  • Sep 01, 2018
  • IEEE Transactions on Software Engineering
  • Jaechang Nam +4
  • PDF
  • Research Article
  • Citations4

Landmark-Based Domain Adaptation and Selective Pseudo-Labeling for Heterogeneous Defect Prediction

  • Jan 22, 2024
  • Electronics
  • Yidan Chen +1
  • Book Chapter
  • Citations4

Handling Class Imbalance Problem in Heterogeneous Cross-Project Defect Prediction

  • Aug 02, 2020
  • Rohit Vashisht +1
  • Conference Article
  • Citations5

Two-stage cost-sensitive local models for heterogeneous cross-project defect prediction

  • Jun 01, 2022
  • Yan Huang +1
  • Research Article
  • Citations18

A Data Transfer and Relevant Metrics Matching Based Approach for Heterogeneous Defect Prediction

  • Mar 01, 2023
  • IEEE Transactions on Software Engineering
  • Pravas Ranjan Bal +1
  • Research Article
  • Citations32

MHCPDP: multi-source heterogeneous cross-project defect prediction via multi-source transfer learning and autoencoder

  • Apr 27, 2021
  • Software Quality Journal
  • Jie Wu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.