Confronta i metodi
Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.
| Longformer / BigBird× | Rete di Attenzione su Grafo× | Mixture of Experts× | |
|---|---|---|---|
| Campo | Apprendimento profondo | Apprendimento profondo | Apprendimento profondo |
| Famiglia | Machine learning | Machine learning | Machine learning |
| Anno di origine≠ | 2020 | 2018 | 2017 |
| Ideatore≠ | Beltagy, Peters & Cohan (Longformer); Zaheer et al. (BigBird) | Veličković, P. et al. | Shazeer, N. et al. |
| Tipo≠ | Sparse-attention Transformer for long sequences | Graph neural network (attention-based) | Sparse neural network architecture (conditional computation) |
| Fonte seminale≠ | 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 ↗ | Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗ |
| Alias≠ | 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 | Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts |
| Correlati≠ | 4 | 4 | 3 |
| Sintesi≠ | 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). | Mixture of Experts (MoE) is a sparse neural-network architecture, introduced by Shazeer and colleagues in 2017 with the sparsely-gated MoE layer, in which only a subset of expert sub-networks is activated for each input. As seen in models such as Switch Transformer and Mixtral, it holds computation cost fixed even as the total parameter count grows. |
| ScholarGateInsieme di dati ↗ |
|
|
|