方法对比

	知识蒸馏	XGBoost
领域	深度学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2015	2016
提出者	Hinton, G., Vinyals, O. & Dean, J.	Chen, T. & Guestrin, C.
类型	Neural network compression (teacher–student)	Ensemble (gradient-boosted decision trees)
开创性文献	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794.
别名	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	XGBoost, extreme gradient boosting, scalable tree boosting
相关	5	5
摘要	Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.	XGBoost (Extreme Gradient Boosting) is a scalable tree-boosting algorithm introduced by Tianqi Chen and Carlos Guestrin in 2016. It builds a strong predictor by adding decision trees one at a time, each correcting the errors left by the trees before it, and is a powerful prediction method widely used in competitions.