Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Mixture of Experts× | Sieć uwagi grafowej× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania≠ | 2017 | 2018 |
| Twórca≠ | Shazeer, N. et al. | Veličković, P. et al. |
| Typ≠ | Sparse neural network architecture (conditional computation) | Graph neural network (attention-based) |
| Źródło pierwotne≠ | Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗ | Veličković, P. et al. (2018). Graph Attention Networks. ICLR. link ↗ |
| Inne nazwy≠ | Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts | Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network |
| Pokrewne≠ | 3 | 4 |
| Podsumowanie≠ | 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. | 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). |
| ScholarGateZbiór danych ↗ |
|
|