@inproceedings{nguyen-he-2025-swift,
title = "Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding",
author = "Nguyen, Nguyen Binh and
He, Yang",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.49/",
pages = "726--739",
abstract = "Dataset pruning aims to select a subset of a dataset for efficient model training. While data efficiency in natural language processing has primarily focused on cross-corpus scenarios during model pre-training, efficient dataset pruning for task-specific fine-tuning across diverse datasets remains challenging due to variability in dataset sizes, data distributions, class imbalance and label spaces. Current cross-dataset pruning techniques for fine-tuning often rely on computationally expensive sample ranking processes, typically requiring full dataset training or reference models. We address this gap by proposing Swift Cross-Dataset Pruning (SCDP). Specifically, our approach uses TF-IDF embeddings with geometric median to rapidly evaluate sample importance. We then apply dataset size-adaptive pruning to ensure diversity: for smaller datasets, we retain examples far from the geometric median, while for larger ones, we employ distance-based stratified pruning. Experimental results on six diverse datasets demonstrate the effectiveness of our method, spanning various tasks and scales while significantly reducing computational resources."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-he-2025-swift">
<titleInfo>
<title>Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="given">Binh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</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">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dataset pruning aims to select a subset of a dataset for efficient model training. While data efficiency in natural language processing has primarily focused on cross-corpus scenarios during model pre-training, efficient dataset pruning for task-specific fine-tuning across diverse datasets remains challenging due to variability in dataset sizes, data distributions, class imbalance and label spaces. Current cross-dataset pruning techniques for fine-tuning often rely on computationally expensive sample ranking processes, typically requiring full dataset training or reference models. We address this gap by proposing Swift Cross-Dataset Pruning (SCDP). Specifically, our approach uses TF-IDF embeddings with geometric median to rapidly evaluate sample importance. We then apply dataset size-adaptive pruning to ensure diversity: for smaller datasets, we retain examples far from the geometric median, while for larger ones, we employ distance-based stratified pruning. Experimental results on six diverse datasets demonstrate the effectiveness of our method, spanning various tasks and scales while significantly reducing computational resources.</abstract>
<identifier type="citekey">nguyen-he-2025-swift</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.49/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>726</start>
<end>739</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding
%A Nguyen, Nguyen Binh
%A He, Yang
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F nguyen-he-2025-swift
%X Dataset pruning aims to select a subset of a dataset for efficient model training. While data efficiency in natural language processing has primarily focused on cross-corpus scenarios during model pre-training, efficient dataset pruning for task-specific fine-tuning across diverse datasets remains challenging due to variability in dataset sizes, data distributions, class imbalance and label spaces. Current cross-dataset pruning techniques for fine-tuning often rely on computationally expensive sample ranking processes, typically requiring full dataset training or reference models. We address this gap by proposing Swift Cross-Dataset Pruning (SCDP). Specifically, our approach uses TF-IDF embeddings with geometric median to rapidly evaluate sample importance. We then apply dataset size-adaptive pruning to ensure diversity: for smaller datasets, we retain examples far from the geometric median, while for larger ones, we employ distance-based stratified pruning. Experimental results on six diverse datasets demonstrate the effectiveness of our method, spanning various tasks and scales while significantly reducing computational resources.
%U https://aclanthology.org/2025.coling-main.49/
%P 726-739
Markdown (Informal)
[Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding](https://aclanthology.org/2025.coling-main.49/) (Nguyen & He, COLING 2025)
ACL