So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Longformer / BigBird× | Mạng Hồi quy Đồ thị (Graph Attention Network - GAT)× | Rừng ngẫu nhiên× | |
|---|---|---|---|
| Lĩnh vực≠ | Học sâu | Học sâu | Học máy |
| Họ | Machine learning | Machine learning | Machine learning |
| Năm ra đời≠ | 2020 | 2018 | 2001 |
| Người khởi xướng≠ | Beltagy, Peters & Cohan (Longformer); Zaheer et al. (BigBird) | Veličković, P. et al. | Breiman, L. |
| Loại≠ | Sparse-attention Transformer for long sequences | Graph neural network (attention-based) | Ensemble (bagging of decision trees) |
| Công trình gốc≠ | Beltagy, I., Peters, M. E. & Cohan, A. (2020). Longformer: The Long-Document Transformer. arXiv. link ↗ | Veličković, P. et al. (2018). Graph Attention Networks. ICLR. link ↗ | Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. DOI ↗ |
| Tên gọi khác | Uzun Dizi Transformer (Longformer / BigBird), uzun dizi transformer, long-document transformer, sparse-attention transformer | Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network | Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble |
| Liên quan | 4 | 4 | 4 |
| Tóm tắt≠ | Long-sequence Transformers such as Longformer (Beltagy, Peters & Cohan, 2020) and BigBird (Zaheer et al., 2020) replace the standard Transformer's O(n²) attention with sparse attention patterns that scale linearly, O(n), with sequence length. This lets a single model attend over thousands of tokens — full documents, legal texts, or genomic sequences — that would not fit a conventional Transformer. | The Graph Attention Network (GAT), introduced by Veličković and colleagues in 2018, is a graph neural network variant that learns how much importance to assign to each neighbouring node through a self-attention mechanism. On heterogeneous neighbourhoods and relational classification it produces results superior to graph convolutional networks (GCN). | Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree. |
| ScholarGateBộ dữ liệu ↗ |
|
|
|