ScholarGate
Asystent

Porównaj metody

Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.

Sieć uwagi grafowej×Mixture of Experts×
DziedzinaUczenie głębokieUczenie głębokie
RodzinaMachine learningMachine learning
Rok powstania20182017
TwórcaVeličković, P. et al.Shazeer, N. et al.
TypGraph neural network (attention-based)Sparse neural network architecture (conditional computation)
Źródło pierwotneVeličković, 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 ↗
Inne nazwyGraf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural networkUzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
Pokrewne43
PodsumowanieThe 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.
ScholarGateZbiór danych
  1. v1
  2. 2 Źródła
  3. PUBLISHED
  1. v1
  2. 2 Źródła
  3. PUBLISHED

Przejdź do wyszukiwania Pobierz slajdy

ScholarGatePorównaj metody: Graph Attention Network · Mixture of Experts. Pobrano 2026-06-20 z https://scholargate.app/pl/compare