Порівняння методів

	Генеративна змагальна мережа Вассерштейна (WGAN)	Дифузійна модель	Генеративно-змагальна мережа
Галузь	Глибоке навчання	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning	Machine learning
Рік появи	2017	2020	2014
Автор методу	Martín Arjovsky, Soumith Chintala & Léon Bottou	Ho, J., Jain, A. & Abbeel, P.	Goodfellow, I. et al.
Тип	Generative adversarial network variant	Generative deep learning (denoising diffusion)	Generative deep learning (adversarial two-network game)
Основоположне джерело	Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223.	Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
Інші назви	WGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN	Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Пов'язані	3	4	4
Підсумок	Wasserstein GAN (WGAN) is a generative adversarial network variant introduced by Arjovsky, Chintala, and Bottou in 2017 that replaces the Jensen-Shannon divergence used in the original GAN with the Wasserstein-1 (Earth Mover) distance. This substitution provides a theoretically grounded training objective that yields more stable optimization and a loss value that correlates meaningfully with generated sample quality, addressing the notorious mode collapse and vanishing gradient problems of standard GANs.	A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling.	A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation.