Sammenlign metoder
Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.
| Blanding av eksperter× | Graph Attention Network× | XGBoost× | |
|---|---|---|---|
| Fagfelt≠ | Dyp læring | Dyp læring | Maskinlæring |
| Familie | Machine learning | Machine learning | Machine learning |
| Opprinnelsesår≠ | 2017 | 2018 | 2016 |
| Opphavsperson≠ | 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) |
| Opprinnelig kilde≠ | 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 ↗ |
| 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 |
| Relaterte≠ | 3 | 4 | 5 |
| Sammendrag≠ | 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. |
| ScholarGateDatasett ↗ |
|
|
|