Sammenlign metoder
Gennemgå dine valgte metoder side om side; rækker, der afviger, er fremhævet.
| Grafneuralt netværk× | Random Forest× | |
|---|---|---|
| Fagområde≠ | Dyb læring | Maskinlæring |
| Familie | Machine learning | Machine learning |
| Oprindelsesår≠ | 2017 | 2001 |
| Ophavsperson≠ | Kipf, T.N. & Welling, M. | Breiman, L. |
| Type≠ | Deep learning on graph-structured data | Ensemble (bagging of decision trees) |
| Oprindelig kilde≠ | Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. ICLR. link ↗ | Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. DOI ↗ |
| Aliasser | Grafik Sinir Ağı (GNN), GNN, graph neural net, graph convolutional network | Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble |
| Relaterede | 4 | 4 |
| Resumé≠ | A Graph Neural Network (GNN) is a deep learning method, popularised by Kipf and Welling in 2017 with the Graph Convolutional Network, that learns from the relationships in network (graph) structures made of nodes and edges. It is designed for data that is naturally relational, such as social networks, molecular structures, and recommendation systems. | 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. |
| ScholarGateDatasæt ↗ |
|
|