@inproceedings{lin-etal-2021-weight,
title = "Weight Distillation: Transferring the Knowledge in Neural Network Parameters",
author = "Lin, Ye and
Li, Yanyang and
Wang, Ziyang and
Li, Bei and
Du, Quan and
Xiao, Tong and
Zhu, Jingbo",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.162/",
doi = "10.18653/v1/2021.acl-long.162",
pages = "2076--2088",
abstract = "Knowledge distillation has been proven to be effective in model acceleration and compression. It transfers knowledge from a large neural network to a small one by using the large neural network predictions as targets of the small neural network. But this way ignores the knowledge inside the large neural networks, e.g., parameters. Our preliminary study as well as the recent success in pre-training suggests that transferring parameters are more effective in distilling knowledge. In this paper, we propose Weight Distillation to transfer the knowledge in parameters of a large neural network to a small neural network through a parameter generator. On the WMT16 En-Ro, NIST12 Zh-En, and WMT14 En-De machine translation tasks, our experiments show that weight distillation learns a small network that is 1.88 2.94x faster than the large network but with competitive BLEU performance. When fixing the size of small networks, weight distillation outperforms knowledge distillation by 0.51 1.82 BLEU points."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2021-weight">
<titleInfo>
<title>Weight Distillation: Transferring the Knowledge in Neural Network Parameters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge distillation has been proven to be effective in model acceleration and compression. It transfers knowledge from a large neural network to a small one by using the large neural network predictions as targets of the small neural network. But this way ignores the knowledge inside the large neural networks, e.g., parameters. Our preliminary study as well as the recent success in pre-training suggests that transferring parameters are more effective in distilling knowledge. In this paper, we propose Weight Distillation to transfer the knowledge in parameters of a large neural network to a small neural network through a parameter generator. On the WMT16 En-Ro, NIST12 Zh-En, and WMT14 En-De machine translation tasks, our experiments show that weight distillation learns a small network that is 1.88 2.94x faster than the large network but with competitive BLEU performance. When fixing the size of small networks, weight distillation outperforms knowledge distillation by 0.51 1.82 BLEU points.</abstract>
<identifier type="citekey">lin-etal-2021-weight</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.162</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.162/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2076</start>
<end>2088</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Weight Distillation: Transferring the Knowledge in Neural Network Parameters
%A Lin, Ye
%A Li, Yanyang
%A Wang, Ziyang
%A Li, Bei
%A Du, Quan
%A Xiao, Tong
%A Zhu, Jingbo
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F lin-etal-2021-weight
%X Knowledge distillation has been proven to be effective in model acceleration and compression. It transfers knowledge from a large neural network to a small one by using the large neural network predictions as targets of the small neural network. But this way ignores the knowledge inside the large neural networks, e.g., parameters. Our preliminary study as well as the recent success in pre-training suggests that transferring parameters are more effective in distilling knowledge. In this paper, we propose Weight Distillation to transfer the knowledge in parameters of a large neural network to a small neural network through a parameter generator. On the WMT16 En-Ro, NIST12 Zh-En, and WMT14 En-De machine translation tasks, our experiments show that weight distillation learns a small network that is 1.88 2.94x faster than the large network but with competitive BLEU performance. When fixing the size of small networks, weight distillation outperforms knowledge distillation by 0.51 1.82 BLEU points.
%R 10.18653/v1/2021.acl-long.162
%U https://aclanthology.org/2021.acl-long.162/
%U https://doi.org/10.18653/v1/2021.acl-long.162
%P 2076-2088
Markdown (Informal)
[Weight Distillation: Transferring the Knowledge in Neural Network Parameters](https://aclanthology.org/2021.acl-long.162/) (Lin et al., ACL-IJCNLP 2021)
ACL
- Ye Lin, Yanyang Li, Ziyang Wang, Bei Li, Quan Du, Tong Xiao, and Jingbo Zhu. 2021. Weight Distillation: Transferring the Knowledge in Neural Network Parameters. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2076–2088, Online. Association for Computational Linguistics.