قارن الطرق

	مزيج الخبراء	شبكة الانتباه الرسومية
المجال	التعلم العميق	التعلم العميق
العائلة	Machine learning	Machine learning
سنة النشأة	2017	2018
صاحب الطريقة	Shazeer, N. et al.	Veličković, P. et al.
النوع	Sparse neural network architecture (conditional computation)	Graph neural network (attention-based)
المصدر التأسيسي	Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538	Veličković, P. et al. (2018). Graph Attention Networks. ICLR.
الأسماء البديلة	Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts	Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network
ذات صلة	3	4
الملخص	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.	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).