Comparer des méthodes

	Processus Gaussien Auto-supervisé	Autoencodeur Variationnel
Domaine	Apprentissage automatique	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2019–2021	2014
Auteur d'origine	Fortuin, V. et al.; broader self-supervised GP literature	Kingma, D. P. & Welling, M.
Type	Probabilistic model (self-supervised GP pretraining + kernel learning)	Deep generative latent-variable model (encoder–decoder)
Source fondatrice	Fortuin, V., Rätsch, G., & Mandt, S. (2020). GP-VAE: Deep probabilistic time series imputation using Gaussian process variational autoencoders. Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 108, 1651–1661.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
Alias	SSL-GP, self-supervised GP, self-supervised GPR, self-supervised Gaussian process regression	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
Apparentées	6	5
Résumé	Self-supervised Gaussian Process (SSL-GP) combines the principled uncertainty quantification of Gaussian processes with self-supervised pretraining, learning expressive kernels or latent representations from unlabeled data before fitting a GP on a small labeled set. This makes the approach especially powerful in low-labeled-data regimes where a conventional GP would overfit or produce poorly calibrated uncertainty estimates.	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.