ScholarGate
Asistente

Comparar métodos

Revisa los métodos seleccionados uno junto a otro; las filas que difieren aparecen resaltadas.

Mezcla de Expertos×Red de Atención Gráfica×
CampoAprendizaje profundoAprendizaje profundo
FamiliaMachine learningMachine learning
Año de origen20172018
Autor originalShazeer, N. et al.Veličković, P. et al.
TipoSparse neural network architecture (conditional computation)Graph neural network (attention-based)
Fuente seminalShazeer, 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 ↗
AliasUzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of expertsGraf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network
Relacionados34
ResumenMixture 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).
ScholarGateConjunto de datos
  1. v1
  2. 2 Fuentes
  3. PUBLISHED
  1. v1
  2. 2 Fuentes
  3. PUBLISHED

Ir a la búsqueda Descargar diapositivas

ScholarGateComparar métodos: Mixture of Experts · Graph Attention Network. Recuperado el 2026-06-19 de https://scholargate.app/es/compare