So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| LoRA và PEFT× | XGBoost× | |
|---|---|---|
| Lĩnh vực≠ | Học sâu | Học máy |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 2022 | 2016 |
| Người khởi xướng≠ | Hu, E. J. et al.; Lester, B. et al. | Chen, T. & Guestrin, C. |
| Loại≠ | Parameter-efficient fine-tuning of large pretrained models | Ensemble (gradient-boosted decision trees) |
| Công trình gốc≠ | Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR. link ↗ | Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794. DOI ↗ |
| Tên gọi khác≠ | LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning | XGBoost, extreme gradient boosting, scalable tree boosting |
| Liên quan | 5 | 5 |
| Tóm tắt≠ | LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched. | XGBoost (Extreme Gradient Boosting) is a scalable tree-boosting algorithm introduced by Tianqi Chen and Carlos Guestrin in 2016. It builds a strong predictor by adding decision trees one at a time, each correcting the errors left by the trees before it, and is a powerful prediction method widely used in competitions. |
| ScholarGateBộ dữ liệu ↗ |
|
|