Comparer des méthodes

	Mélange d'experts	Réseau d'attention sur graphe	XGBoost
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2017	2018	2016
Auteur d'origine	Shazeer, N. et al.	Veličković, P. et al.	Chen, T. & Guestrin, C.
Type	Sparse neural network architecture (conditional computation)	Graph neural network (attention-based)	Ensemble (gradient-boosted decision trees)
Source fondatrice	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.	Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794.
Alias	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	XGBoost, extreme gradient boosting, scalable tree boosting
Apparentées	3	4	5
Résumé	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).	XGBoost (Extreme Gradient Boosting) is a scalable tree-boosting algorithm introduced by Tianqi Chen and Carlos Guestrin in 2016. It builds a strong predictor by adding decision trees one at a time, each correcting the errors left by the trees before it, and is a powerful prediction method widely used in competitions.