@inproceedings{zhou-etal-2024-quest,
title = "{QUEST}: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity Hardware",
author = "Zhou, Chuang and
Dong, Junnan and
Huang, Xiao and
Liu, Zirui and
Zhou, Kaixiong and
Xu, Zhaozhuo",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.226",
pages = "3929--3940",
abstract = "Extreme multi-label text classification (EMTC) involves predicting multiple labels from a vast pool of candidates based on a user{'}s textual query. While traditional BERT-based methods have shown limited success, large language models (LLMs) have brought new possibilities. It is promising to leverage their remarkable comprehension ability to understand textual queries. However, implementing LLMs is non-trivial for two main reasons. Firstly, real-world EMTC datasets can be extremely large, with candidate product pairs reaching up to ten million in real-world scenarios, which poses significant challenges in data ingestion. Secondly, the large size of LLMs makes computation and memory demands prohibitive for EMTC applications. To this end, we propose QUEST, a Quantized and Efficient Learning with Sampling Technique. QUEST includes a tailored hash sampling module that reduces the data volume to one-fourth of its original size. Additionally, we perform compressive fine-tuning LLMs with only twenty thousand trainable parameters, largely reducing computational requirements. Extensive experiments demonstrate that QUEST outperforms existing methods while requiring fewer computational resources, unlocking efficient EMTC on commodity hardware such as a single Nvidia RTX 3090 GPU with 24 GB of memory.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2024-quest">
<titleInfo>
<title>QUEST: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity Hardware</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chuang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junnan</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zirui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaixiong</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaozhuo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extreme multi-label text classification (EMTC) involves predicting multiple labels from a vast pool of candidates based on a user’s textual query. While traditional BERT-based methods have shown limited success, large language models (LLMs) have brought new possibilities. It is promising to leverage their remarkable comprehension ability to understand textual queries. However, implementing LLMs is non-trivial for two main reasons. Firstly, real-world EMTC datasets can be extremely large, with candidate product pairs reaching up to ten million in real-world scenarios, which poses significant challenges in data ingestion. Secondly, the large size of LLMs makes computation and memory demands prohibitive for EMTC applications. To this end, we propose QUEST, a Quantized and Efficient Learning with Sampling Technique. QUEST includes a tailored hash sampling module that reduces the data volume to one-fourth of its original size. Additionally, we perform compressive fine-tuning LLMs with only twenty thousand trainable parameters, largely reducing computational requirements. Extensive experiments demonstrate that QUEST outperforms existing methods while requiring fewer computational resources, unlocking efficient EMTC on commodity hardware such as a single Nvidia RTX 3090 GPU with 24 GB of memory.</abstract>
<identifier type="citekey">zhou-etal-2024-quest</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.226</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>3929</start>
<end>3940</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QUEST: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity Hardware
%A Zhou, Chuang
%A Dong, Junnan
%A Huang, Xiao
%A Liu, Zirui
%A Zhou, Kaixiong
%A Xu, Zhaozhuo
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zhou-etal-2024-quest
%X Extreme multi-label text classification (EMTC) involves predicting multiple labels from a vast pool of candidates based on a user’s textual query. While traditional BERT-based methods have shown limited success, large language models (LLMs) have brought new possibilities. It is promising to leverage their remarkable comprehension ability to understand textual queries. However, implementing LLMs is non-trivial for two main reasons. Firstly, real-world EMTC datasets can be extremely large, with candidate product pairs reaching up to ten million in real-world scenarios, which poses significant challenges in data ingestion. Secondly, the large size of LLMs makes computation and memory demands prohibitive for EMTC applications. To this end, we propose QUEST, a Quantized and Efficient Learning with Sampling Technique. QUEST includes a tailored hash sampling module that reduces the data volume to one-fourth of its original size. Additionally, we perform compressive fine-tuning LLMs with only twenty thousand trainable parameters, largely reducing computational requirements. Extensive experiments demonstrate that QUEST outperforms existing methods while requiring fewer computational resources, unlocking efficient EMTC on commodity hardware such as a single Nvidia RTX 3090 GPU with 24 GB of memory.
%U https://aclanthology.org/2024.findings-emnlp.226
%P 3929-3940
Markdown (Informal)
[QUEST: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity Hardware](https://aclanthology.org/2024.findings-emnlp.226) (Zhou et al., Findings 2024)
ACL