1. A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models
- Author
-
Lee, Hayeon, Hou, Rui, Kim, Jongpil, Liang, Davis, Hwang, Sung Ju, and Min, Alexander
- Subjects
FOS: Computer and information sciences ,Artificial Intelligence (cs.AI) ,Computer Science - Computation and Language ,Computer Science - Artificial Intelligence ,Computation and Language (cs.CL) - Abstract
Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance. Previous studies have shown that DWT can be effective in the vision domain and natural language processing (NLP) pre-training stage. Specifically, DWT shows promise in practical scenarios, such as enhancing new generation or larger models using pre-trained yet older or smaller models and lacking a resource budget. However, the optimal conditions for using DWT have yet to be fully investigated in NLP pre-training. Therefore, this study examines three key factors to optimize DWT, distinct from those used in the vision domain or traditional knowledge distillation. These factors are: (i) the impact of teacher model quality on DWT effectiveness, (ii) guidelines for adjusting the weighting value for DWT loss, and (iii) the impact of parameter remapping as a student model initialization technique for DWT., Findings of ACL 2023
- Published
- 2023