ScholarGate
Assistent

Võrdle meetodeid

Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.

Ekspertide segu×Graafiline tähelepanuvõrk×
ValdkondSüvaõpeSüvaõpe
PerekondMachine learningMachine learning
Tekkeaasta20172018
LoojaShazeer, N. et al.Veličković, P. et al.
TüüpSparse neural network architecture (conditional computation)Graph neural network (attention-based)
AlgallikasShazeer, 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 ↗
RööpnimetusedUzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of expertsGraf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network
Seotud34
KokkuvõteMixture 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).
ScholarGateAndmestik
  1. v1
  2. 2 Allikad
  3. PUBLISHED
  1. v1
  2. 2 Allikad
  3. PUBLISHED

Mine otsingusse Laadi slaidid alla

ScholarGateVõrdle meetodeid: Mixture of Experts · Graph Attention Network. Loetud 2026-06-19 aadressilt https://scholargate.app/et/compare