Do we need Label Regularization to Fine-tune Pre-trained Language Models?

[PDF] arxiv.org

Boosting Commit Classification with Contrastive Learning

J Tong, Z Wang, X Rui - arXiv preprint arXiv:2308.08263, 2023 - arxiv.org
Commit Classification (CC) is an important task in software maintenance, which helps
software developers classify code changes into different types according to their nature and …
被引用次数：1 相关文章 所有 3 个版本
[PDF] arxiv.org

LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization

P Lu, A Rashid, I Kobyzev, M Rezagholizadeh… - arXiv preprint arXiv …, 2023 - arxiv.org
Regularization techniques are crucial to improving the generalization performance and
training efficiency of deep neural networks. Many deep learning algorithms rely on weight …
相关文章 所有 4 个版本