Chen Liang, Simiao Zuo, Qingru Zhang, Pengcheng He, Weizhu Chen, Tuo Zhao. Less is More: Task-aware Layer-wise Distillation for Language Model Compression. In Andreas Krause 0001, Emma Brunskill, KyungHyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett, editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA. Volume 202 of Proceedings of Machine Learning Research, pages 20852-20867, PMLR, 2023. [doi]
@inproceedings{LiangZZHCZ23,
title = {Less is More: Task-aware Layer-wise Distillation for Language Model Compression},
author = {Chen Liang and Simiao Zuo and Qingru Zhang and Pengcheng He and Weizhu Chen and Tuo Zhao},
year = {2023},
url = {https://proceedings.mlr.press/v202/liang23j.html},
researchr = {https://researchr.org/publication/LiangZZHCZ23},
cites = {0},
citedby = {0},
pages = {20852-20867},
booktitle = {International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA},
editor = {Andreas Krause 0001 and Emma Brunskill and KyungHyun Cho and Barbara Engelhardt and Sivan Sabato and Jonathan Scarlett},
volume = {202},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}