เปรียบเทียบวิธี

	LoRA และ PEFT	โครงข่ายปฏิปักษ์เชิงกำเนิด	ตัวเข้ารหัสอัตโนมัติแบบแปรผัน
สาขาวิชา	การเรียนรู้เชิงลึก	การเรียนรู้เชิงลึก	การเรียนรู้เชิงลึก
ตระกูล	Machine learning	Machine learning	Machine learning
ปีกำเนิด	2022	2014	2014
ผู้ริเริ่ม	Hu, E. J. et al.; Lester, B. et al.	Goodfellow, I. et al.	Kingma, D. P. & Welling, M.
ประเภท	Parameter-efficient fine-tuning of large pretrained models	Generative deep learning (adversarial two-network game)	Deep generative latent-variable model (encoder–decoder)
แหล่งต้นตำรับ	Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
ชื่อเรียกอื่น	LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
ที่เกี่ยวข้อง	5	4	5
สรุป	LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched.	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.	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.