ScholarGate
Assistent

Sammenlign metoder

Gennemgå dine valgte metoder side om side; rækker, der afviger, er fremhævet.

Graph Attention Network×Mixture of Experts×
FagområdeDyb læringDyb læring
FamilieMachine learningMachine learning
Oprindelsesår20182017
OphavspersonVeličković, P. et al.Shazeer, N. et al.
TypeGraph neural network (attention-based)Sparse neural network architecture (conditional computation)
Oprindelig kildeVeličković, 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 ↗
AliasserGraf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural networkUzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
Relaterede43
ResuméThe 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.
ScholarGateDatasæt
  1. v1
  2. 2 Kilder
  3. PUBLISHED
  1. v1
  2. 2 Kilder
  3. PUBLISHED

Gå til søgning Hent slides

ScholarGateSammenlign metoder: Graph Attention Network · Mixture of Experts. Hentet 2026-06-20 fra https://scholargate.app/da/compare