TokenGated-CodeBERT With Lightweight Attention-Based Token Selection for Software Defect Prediction
Class imbalance poses a key challenge in defective code module detection, severely limiting the performance of deep learning models. To address this issue, we propose TokenGated-CodeBERT, a new methodology designed for scenarios with severe class imbalance. Constructed on the basis of vanilla CodeBE...
Kaydedildi:
| Asıl Yazarlar: | , , |
|---|---|
| Materyal Türü: | Artigo |
| Dil: | Inglês |
| Baskı/Yayın Bilgisi: |
IEEE
2026-01-01
|
| Seri Bilgileri: | IEEE Access |
| Konular: | |
| Online Erişim: | https://ieeexplore.ieee.org/document/11594087/ |
| Etiketler: |
Etiket eklenmemiş, İlk siz ekleyin!
|