方法对比

	可解释变分自编码器	微调变分自编码器
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2013–2017	2014 (VAE); fine-tuning practice from 2015 onward
提出者	Kingma, D. P. & Welling, M. (VAE); Higgins et al. (beta-VAE for disentanglement)	Kingma, D. P. & Welling, M. (VAE); fine-tuning strategy from transfer learning literature
类型	Generative model with interpretable latent space	Generative model with fine-tuning
开创性文献	Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014).	Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014).
别名	XVAE, Interpretable VAE, Disentangled Variational Autoencoder, Explainable Generative Model	fine-tuned VAE, domain-adapted VAE, transfer-learned VAE, adapted variational autoencoder
相关	4	6
摘要	An Explainable Variational Autoencoder (XVAE) extends the standard VAE framework with techniques that make its latent space interpretable: disentangling latent dimensions so each corresponds to a human-understandable factor, or post-hoc attribution methods (SHAP, integrated gradients) that trace reconstructions back to input features. It retains the VAE's generative power while adding transparency required in scientific and high-stakes applications.	A Fine-Tuned Variational Autoencoder begins with a VAE pre-trained on a large source dataset and then continues training on a smaller target-domain dataset. This approach adapts the learned latent representation and generative capacity to new data, preserving general structure while specializing to the target distribution — yielding better results than training from scratch when labeled or large target data is scarce.