ScholarGate
Asistents

Salīdzināt metodes

Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.

Grafu uzmanības tīkls (Graph Attention Network, GAT)×Ekspertu maisījums×
NozareDziļā mācīšanāsDziļā mācīšanās
SaimeMachine learningMachine learning
Izcelsmes gads20182017
AutorsVeličković, P. et al.Shazeer, N. et al.
TipsGraph neural network (attention-based)Sparse neural network architecture (conditional computation)
PirmavotsVeličković, 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 ↗
Citi nosaukumiGraf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural networkUzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
Saistītās43
KopsavilkumsThe 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.
ScholarGateDatu kopa
  1. v1
  2. 2 Avoti
  3. PUBLISHED
  1. v1
  2. 2 Avoti
  3. PUBLISHED

Doties uz meklēšanu Lejupielādēt slaidus

ScholarGateSalīdzināt metodes: Graph Attention Network · Mixture of Experts. Izgūts 2026-06-20 no https://scholargate.app/lv/compare