So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Tự chú ý đa đầu× | Tinh chỉnh BERT× | LoRA và PEFT× | |
|---|---|---|---|
| Lĩnh vực | Học sâu | Học sâu | Học sâu |
| Họ | Machine learning | Machine learning | Machine learning |
| Năm ra đời≠ | 2017 | 2019 | 2022 |
| Người khởi xướng≠ | Vaswani, A. et al. | Devlin, J. et al. | Hu, E. J. et al.; Lester, B. et al. |
| Loại≠ | Attention mechanism (Transformer core) | Transfer learning (fine-tuning a pre-trained transformer) | Parameter-efficient fine-tuning of large pretrained models |
| Công trình gốc≠ | Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS. link ↗ | Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL. DOI ↗ | Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR. link ↗ |
| Tên gọi khác≠ | Öz-Dikkat ve Çok Başlı Dikkat (Multi-Head Self-Attention), öz-dikkat, multi-head attention, scaled dot-product attention | BERT İnce Ayar (Fine-Tuning), BERT ince ayar, fine-tuning BERT, transfer learning with BERT | LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning |
| Liên quan | 5 | 5 | 5 |
| Tóm tắt≠ | Multi-head self-attention, introduced by Vaswani and colleagues in 2017, is the mechanism that lets every position in a sequence compute its relationship to all other positions in parallel. It is the core of the Transformer architecture and the foundation underneath BERT, GPT, and T5. | BERT fine-tuning, building on the BERT model introduced by Devlin and colleagues in 2019, re-trains a pre-trained BERT model on a small labelled dataset for a target task such as classification, named-entity recognition, or question answering. Through transfer learning it reaches high performance even with relatively little task-specific data. | 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. |
| ScholarGateBộ dữ liệu ↗ |
|
|
|