So sánh phương pháp

	Wasserstein GAN (WGAN)	Generative Adversarial Network
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2017	2014
Người khởi xướng	Martín Arjovsky, Soumith Chintala & Léon Bottou	Goodfellow, I. et al.
Loại	Generative adversarial network variant	Generative deep learning (adversarial two-network game)
Công trình gốc	Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
Tên gọi khác	WGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Liên quan	3	4
Tóm tắt	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 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.