방법 비교

	준지도 학습 확산 모델	Variational Autoencoder
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2020–2022	2014
창시자	Multiple groups (Ho et al., Song et al., and successors)	Kingma, D. P. & Welling, M.
유형	Generative model with semi-supervised guidance	Deep generative latent-variable model (encoder–decoder)
원전	Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015). Deep Unsupervised Learning using Nonequilibrium Thermodynamics. Proceedings of the 32nd International Conference on Machine Learning (ICML), 2256–2265.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
별칭	Semi-supervised DDPM, Label-guided diffusion model, Semi-supervised score-based generative model, SSL diffusion	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
관련	3	5
요약	A semi-supervised diffusion model extends the denoising diffusion probabilistic framework to settings where only a fraction of training samples carry class labels. By combining an unconditional diffusion backbone with a lightweight classifier trained on labeled examples, it learns to generate high-quality, label-conditioned outputs while still exploiting the structure in unlabeled data.	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.