Logo image
Back
Unsupervised Code Representation Learning via Contrastive Learning for Cross-Project Defect Prediction
Conference proceeding

Unsupervised Code Representation Learning via Contrastive Learning for Cross-Project Defect Prediction

Hanlin Zhao, Zhiyong Feng and Ruitao Feng
Advanced Intelligent Computing Technology and Applications, pp.3-14
Lecture Notes in Computer Science
22nd International Conference on Intelligent Computing, ICIC 2026, 22nd (Toronto, Canada, 22/07/2026–26/07/2026)
2027
DOI: https://doi.org/10.1007/978-981-92-3441-7_1
Appears in  Recent Faculty of Science and Engineering Publications

Metrics

1 Record Views

Abstract

Cross-project defect prediction (CPDP) is an approach for addressing the situation that historical data is a few for software defect prediction. Many deep learning algorithms applied for CPDP suffer from the huge demand for labeled data to generated feature, which leads to poor performance in CPDP tasks. To address this situation, we propose the method DPCL generating feature without labels, which is aligned feature by comparative learning. During extracting feature, the cascaded architecture of convolutional neural networks and self-attention mechanism is applied for captured the local information and global dependencies. We also design the framework DPCL based on DPCL for CPDP. Experimental studies on the datasets across 17 different software projects show that DPCL achieved an improvement of up to 28.8% in the F1-score on CPDP. We chose the 17 java projects to evaluate our method compared to the baselines.

Details

Logo image