activity
20192022
most citedMulti-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2020

Multi-level Knowledge Distillation via Knowledge Alignment and Correlation

Fei Ding, Yin Yang, Hongxin Hu +2

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge…