เปรียบเทียบวิธี

	Longformer / BigBird	Graph Attention Network	Mixture of Experts
สาขาวิชา	การเรียนรู้เชิงลึก	การเรียนรู้เชิงลึก	การเรียนรู้เชิงลึก
ตระกูล	Machine learning	Machine learning	Machine learning
ปีกำเนิด	2020	2018	2017
ผู้ริเริ่ม	Beltagy, Peters & Cohan (Longformer); Zaheer et al. (BigBird)	Veličković, P. et al.	Shazeer, N. et al.
ประเภท	Sparse-attention Transformer for long sequences	Graph neural network (attention-based)	Sparse neural network architecture (conditional computation)
แหล่งต้นตำรับ	Beltagy, I., Peters, M. E. & Cohan, A. (2020). Longformer: The Long-Document Transformer. arXiv.	Veličković, P. et al. (2018). Graph Attention Networks. ICLR.	Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538
ชื่อเรียกอื่น	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	Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
ที่เกี่ยวข้อง	4	4	3
สรุป	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).	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.