Módszerek összehasonlítása

	Gráfon alapuló figyelmi hálózat	Logistic Regression	Véletlen erdő	Rekurrens neurális hálózat	XGBoost
Tudományterület	Mélytanulás	Kutatási statisztika	Gépi tanulás	Mélytanulás	Gépi tanulás
Módszercsalád	Machine learning	Process / pipeline	Machine learning	Machine learning	Machine learning
Keletkezés éve	2018	1958	2001	1986–1990	2016
Megalkotó	Veličković, P. et al.	David Roxbee Cox	Breiman, L.	Rumelhart, D. E.; Elman, J. L.	Chen, T. & Guestrin, C.
Típus	Graph neural network (attention-based)	Method	Ensemble (bagging of decision trees)	Sequential neural network	Ensemble (gradient-boosted decision trees)
Alapmű	Veličković, P. et al. (2018). Graph Attention Networks. ICLR.	Cox, D. R. (1958). The regression analysis of binary sequences. Journal of the Royal Statistical Society, Series B, 20(2), 215–242.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.	Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.	Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794.
Alternatív nevek	Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network	logit model, binomial logistic regression, LR	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble	RNN, Elman network, Jordan network, simple recurrent network	XGBoost, extreme gradient boosting, scalable tree boosting
Kapcsolódó	4	3	4	3	5
Összefoglaló	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).	Logistic regression is a statistical method for modeling the probability of a binary outcome (disease present/absent, success/failure) as a function of continuous and categorical predictors. Developed by David Roxbee Cox (1958), it solves the problem of predicting categorical outcomes by applying a logistic transformation to constrain predictions to the [0,1] probability interval, enabling accurate risk stratification, diagnostic prediction, and causal inference in epidemiology, medicine, and social science.	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.	A Recurrent Neural Network (RNN) is a class of neural network designed to process sequential data by maintaining a hidden state that carries information across time steps. Introduced in its modern form by Rumelhart et al. (1986) and further shaped by Elman (1990), RNNs became the dominant architecture for sequence modelling in NLP, speech, and time-series analysis before the rise of attention-based models.	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.