@inproceedings{shi-etal-2022-layerconnect,
title = "{L}ayer{C}onnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency",
author = "Shi, Haoxiang and
Zhang, Rongsheng and
Wang, Jiaan and
Wang, Cen and
Zheng, Yinhe and
Sakai, Tetsuya",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.276",
pages = "3120--3126",
abstract = "Pre-trained Language Models (PLMs) are the cornerstone of the modern Natural Language Processing (NLP). However, as PLMs become heavier, fine tuning all their parameters loses their efficiency. Existing parameter-efficient methods generally focus on reducing the trainable parameters in PLMs but neglect the inference speed, which limits the ability to deploy PLMs. In this paper, we propose LayerConnect (hypernetwork-assisted inter-layer connectors) to enhance inference efficiency. Specifically, a light-weight connector with a linear structure is inserted between two Transformer layers, and the parameters inside each connector are tuned by a hypernetwork comprising an interpolator and a down-sampler. We perform extensive experiments on the widely used the GLUE benchmark. The experimental results verify the inference efficiency of our model. Compared to Adapter, our model parameters are reduced to approximately 11.75{\%}, while the performance degradation is kept to less than 5{\%} (2.5 points on average).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2022-layerconnect">
<titleInfo>
<title>LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoxiang</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongsheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinhe</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tetsuya</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained Language Models (PLMs) are the cornerstone of the modern Natural Language Processing (NLP). However, as PLMs become heavier, fine tuning all their parameters loses their efficiency. Existing parameter-efficient methods generally focus on reducing the trainable parameters in PLMs but neglect the inference speed, which limits the ability to deploy PLMs. In this paper, we propose LayerConnect (hypernetwork-assisted inter-layer connectors) to enhance inference efficiency. Specifically, a light-weight connector with a linear structure is inserted between two Transformer layers, and the parameters inside each connector are tuned by a hypernetwork comprising an interpolator and a down-sampler. We perform extensive experiments on the widely used the GLUE benchmark. The experimental results verify the inference efficiency of our model. Compared to Adapter, our model parameters are reduced to approximately 11.75%, while the performance degradation is kept to less than 5% (2.5 points on average).</abstract>
<identifier type="citekey">shi-etal-2022-layerconnect</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.276</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3120</start>
<end>3126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency
%A Shi, Haoxiang
%A Zhang, Rongsheng
%A Wang, Jiaan
%A Wang, Cen
%A Zheng, Yinhe
%A Sakai, Tetsuya
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F shi-etal-2022-layerconnect
%X Pre-trained Language Models (PLMs) are the cornerstone of the modern Natural Language Processing (NLP). However, as PLMs become heavier, fine tuning all their parameters loses their efficiency. Existing parameter-efficient methods generally focus on reducing the trainable parameters in PLMs but neglect the inference speed, which limits the ability to deploy PLMs. In this paper, we propose LayerConnect (hypernetwork-assisted inter-layer connectors) to enhance inference efficiency. Specifically, a light-weight connector with a linear structure is inserted between two Transformer layers, and the parameters inside each connector are tuned by a hypernetwork comprising an interpolator and a down-sampler. We perform extensive experiments on the widely used the GLUE benchmark. The experimental results verify the inference efficiency of our model. Compared to Adapter, our model parameters are reduced to approximately 11.75%, while the performance degradation is kept to less than 5% (2.5 points on average).
%U https://aclanthology.org/2022.coling-1.276
%P 3120-3126
Markdown (Informal)
[LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency](https://aclanthology.org/2022.coling-1.276) (Shi et al., COLING 2022)
ACL