@inproceedings{liu-etal-2023-enhancing-scalability,
title = "Enhancing Scalability of Pre-trained Language Models via Efficient Parameter Sharing",
author = "Liu, Peiyu and
Gao, Ze-Feng and
Chen, Yushuo and
Zhao, Xin and
Wen, Ji-Rong",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.920",
doi = "10.18653/v1/2023.findings-emnlp.920",
pages = "13771--13785",
abstract = "In this paper, we propose a highly parameter-efficient approach to scaling pre-trained language models (PLMs) to a deeper model depth. Unlike prior work that shares all parameters or uses extra blocks, we design a more capable parameter-sharing architecture based on matrix product operator (MPO), an efficient tensor decomposition method to factorize the parameter matrix into a set of local tensors. Based on such a decomposition, we share the important local tensor across all layers for reducing the model size and meanwhile keep layer-specific tensors (also using Adapters) for enhancing the adaptation flexibility. To improve the model training, we further propose a stable initialization algorithm tailored for the MPO-based architecture. Extensive experiments have demonstrated the effectiveness of our proposed model in enhancing scalability and achieving higher performance (i.e., with fewer parameters than BERT-base, we successfully scale the model depth by a factor of 4x and even achieve 0.1 points higher than BERT-large for GLUE score). The code to reproduce the results of this paper can be found at https://github.com/RUCAIBox/MPOBERT-code.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-enhancing-scalability">
<titleInfo>
<title>Enhancing Scalability of Pre-trained Language Models via Efficient Parameter Sharing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peiyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ze-Feng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yushuo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji-Rong</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose a highly parameter-efficient approach to scaling pre-trained language models (PLMs) to a deeper model depth. Unlike prior work that shares all parameters or uses extra blocks, we design a more capable parameter-sharing architecture based on matrix product operator (MPO), an efficient tensor decomposition method to factorize the parameter matrix into a set of local tensors. Based on such a decomposition, we share the important local tensor across all layers for reducing the model size and meanwhile keep layer-specific tensors (also using Adapters) for enhancing the adaptation flexibility. To improve the model training, we further propose a stable initialization algorithm tailored for the MPO-based architecture. Extensive experiments have demonstrated the effectiveness of our proposed model in enhancing scalability and achieving higher performance (i.e., with fewer parameters than BERT-base, we successfully scale the model depth by a factor of 4x and even achieve 0.1 points higher than BERT-large for GLUE score). The code to reproduce the results of this paper can be found at https://github.com/RUCAIBox/MPOBERT-code.</abstract>
<identifier type="citekey">liu-etal-2023-enhancing-scalability</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.920</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.920</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>13771</start>
<end>13785</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Scalability of Pre-trained Language Models via Efficient Parameter Sharing
%A Liu, Peiyu
%A Gao, Ze-Feng
%A Chen, Yushuo
%A Zhao, Xin
%A Wen, Ji-Rong
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F liu-etal-2023-enhancing-scalability
%X In this paper, we propose a highly parameter-efficient approach to scaling pre-trained language models (PLMs) to a deeper model depth. Unlike prior work that shares all parameters or uses extra blocks, we design a more capable parameter-sharing architecture based on matrix product operator (MPO), an efficient tensor decomposition method to factorize the parameter matrix into a set of local tensors. Based on such a decomposition, we share the important local tensor across all layers for reducing the model size and meanwhile keep layer-specific tensors (also using Adapters) for enhancing the adaptation flexibility. To improve the model training, we further propose a stable initialization algorithm tailored for the MPO-based architecture. Extensive experiments have demonstrated the effectiveness of our proposed model in enhancing scalability and achieving higher performance (i.e., with fewer parameters than BERT-base, we successfully scale the model depth by a factor of 4x and even achieve 0.1 points higher than BERT-large for GLUE score). The code to reproduce the results of this paper can be found at https://github.com/RUCAIBox/MPOBERT-code.
%R 10.18653/v1/2023.findings-emnlp.920
%U https://aclanthology.org/2023.findings-emnlp.920
%U https://doi.org/10.18653/v1/2023.findings-emnlp.920
%P 13771-13785
Markdown (Informal)
[Enhancing Scalability of Pre-trained Language Models via Efficient Parameter Sharing](https://aclanthology.org/2023.findings-emnlp.920) (Liu et al., Findings 2023)
ACL