Comparer des méthodes

	Longformer / BigBird	Réseau d'attention sur graphe	Forêt Aléatoire
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2020	2018	2001
Auteur d'origine	Beltagy, Peters & Cohan (Longformer); Zaheer et al. (BigBird)	Veličković, P. et al.	Breiman, L.
Type	Sparse-attention Transformer for long sequences	Graph neural network (attention-based)	Ensemble (bagging of decision trees)
Source fondatrice	Beltagy, I., Peters, M. E. & Cohan, A. (2020). Longformer: The Long-Document Transformer. arXiv.	Veličković, P. et al. (2018). Graph Attention Networks. ICLR.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
Alias	Uzun Dizi Transformer (Longformer / BigBird), uzun dizi transformer, long-document transformer, sparse-attention transformer	Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble
Apparentées	4	4	4
Résumé	Long-sequence Transformers such as Longformer (Beltagy, Peters & Cohan, 2020) and BigBird (Zaheer et al., 2020) replace the standard Transformer's O(n²) attention with sparse attention patterns that scale linearly, O(n), with sequence length. This lets a single model attend over thousands of tokens — full documents, legal texts, or genomic sequences — that would not fit a conventional Transformer.	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).	Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree.