Ping Ma
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes Multi-Teacher Bayesian Knowledge Distillation (MT-BKD), a framework that uses Bayesian inference and teacher-informed priors to improve model compression, enhance predictive accuracy, and quantify uncertainty when distilling knowledge from multiple expert models.
The paper proposes Multi-Teacher Bayesian Knowledge Distillation (MT-BKD), a framework that uses Bayesian inference and teacher-informed priors to improve model compression, enhance predictive accuracy, and quantify uncertainty when distilling knowledge from multiple expert models.
Papers
Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors
Luyang Fang, Yongkai Chen, Jiazhang Cai, Ping Ma +1 more
The paper proposes Multi-Teacher Bayesian Knowledge Distillation (MT-BKD), a framework that uses Bayesian inference and teacher-informed priors to improve model compression, enhance predictive accurac…