So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Mixture of Experts× | Mạng Hồi quy Đồ thị (Graph Attention Network - GAT)× | XGBoost× | |
|---|---|---|---|
| Lĩnh vực≠ | Học sâu | Học sâu | Học máy |
| Họ | Machine learning | Machine learning | Machine learning |
| Năm ra đời≠ | 2017 | 2018 | 2016 |
| Người khởi xướng≠ | Shazeer, N. et al. | Veličković, P. et al. | Chen, T. & Guestrin, C. |
| Loại≠ | Sparse neural network architecture (conditional computation) | Graph neural network (attention-based) | Ensemble (gradient-boosted decision trees) |
| Công trình gốc≠ | Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗ | Veličković, P. et al. (2018). Graph Attention Networks. ICLR. link ↗ | Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794. DOI ↗ |
| Tên gọi khác≠ | 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 |
| Liên quan≠ | 3 | 4 | 5 |
| Tóm tắt≠ | 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. |
| ScholarGateBộ dữ liệu ↗ |
|
|
|