@inproceedings{li-etal-2024-shot-temporal,
title = "Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation",
author = "Li, Bocheng and
Gao, Zhujin and
Zhu, Yongxin and
Yin, Kun and
Cao, Haoyu and
Jiang, Deqiang and
Xu, Linli",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.637",
pages = "7259--7269",
abstract = "Diffusion models have achieved significant success in computer vision and shown immense potential in natural language processing applications, particularly for text generation tasks. However, generating high-quality text using these models often necessitates thousands of iterations, leading to slow sampling rates. Existing acceleration methods either neglect the importance of the distribution of sampling steps, resulting in compromised performance with smaller number of iterations, or require additional training, introducing considerable computational overheads. In this paper, we present Few-shot Temporal Pruning, a novel technique designed to accelerate diffusion models for text generation without supplementary training while effectively leveraging limited data. Employing a Bayesian optimization approach, our method effectively eliminates redundant sampling steps during the sampling process, thereby enhancing the generation speed. A comprehensive evaluation of discrete and continuous diffusion models across various tasks, including machine translation, question generation, and paraphrasing, reveals that our approach achieves competitive performance even with minimal sampling steps after down to less than 1 minute of optimization, yielding a significant acceleration of up to 400x in text generation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-shot-temporal">
<titleInfo>
<title>Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bocheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhujin</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongxin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deqiang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linli</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Diffusion models have achieved significant success in computer vision and shown immense potential in natural language processing applications, particularly for text generation tasks. However, generating high-quality text using these models often necessitates thousands of iterations, leading to slow sampling rates. Existing acceleration methods either neglect the importance of the distribution of sampling steps, resulting in compromised performance with smaller number of iterations, or require additional training, introducing considerable computational overheads. In this paper, we present Few-shot Temporal Pruning, a novel technique designed to accelerate diffusion models for text generation without supplementary training while effectively leveraging limited data. Employing a Bayesian optimization approach, our method effectively eliminates redundant sampling steps during the sampling process, thereby enhancing the generation speed. A comprehensive evaluation of discrete and continuous diffusion models across various tasks, including machine translation, question generation, and paraphrasing, reveals that our approach achieves competitive performance even with minimal sampling steps after down to less than 1 minute of optimization, yielding a significant acceleration of up to 400x in text generation tasks.</abstract>
<identifier type="citekey">li-etal-2024-shot-temporal</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.637</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7259</start>
<end>7269</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation
%A Li, Bocheng
%A Gao, Zhujin
%A Zhu, Yongxin
%A Yin, Kun
%A Cao, Haoyu
%A Jiang, Deqiang
%A Xu, Linli
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F li-etal-2024-shot-temporal
%X Diffusion models have achieved significant success in computer vision and shown immense potential in natural language processing applications, particularly for text generation tasks. However, generating high-quality text using these models often necessitates thousands of iterations, leading to slow sampling rates. Existing acceleration methods either neglect the importance of the distribution of sampling steps, resulting in compromised performance with smaller number of iterations, or require additional training, introducing considerable computational overheads. In this paper, we present Few-shot Temporal Pruning, a novel technique designed to accelerate diffusion models for text generation without supplementary training while effectively leveraging limited data. Employing a Bayesian optimization approach, our method effectively eliminates redundant sampling steps during the sampling process, thereby enhancing the generation speed. A comprehensive evaluation of discrete and continuous diffusion models across various tasks, including machine translation, question generation, and paraphrasing, reveals that our approach achieves competitive performance even with minimal sampling steps after down to less than 1 minute of optimization, yielding a significant acceleration of up to 400x in text generation tasks.
%U https://aclanthology.org/2024.lrec-main.637
%P 7259-7269
Markdown (Informal)
[Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation](https://aclanthology.org/2024.lrec-main.637) (Li et al., LREC-COLING 2024)
ACL
- Bocheng Li, Zhujin Gao, Yongxin Zhu, Kun Yin, Haoyu Cao, Deqiang Jiang, and Linli Xu. 2024. Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7259–7269, Torino, Italia. ELRA and ICCL.