@inproceedings{zhou-etal-2024-orticket,
title = "{ORT}icket: Let One Robust {BERT} Ticket Transfer across Different Tasks",
author = "Zhou, Yuhao and
Chen, Wenxiang and
Zheng, Rui and
Xi, Zhiheng and
Gui, Tao and
Zhang, Qi and
Huang, Xuanjing",
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.1096",
pages = "12527--12538",
abstract = "Pretrained language models can be applied for various downstream tasks but are susceptible to subtle perturbations. Most adversarial defense methods often introduce adversarial training during the fine-tuning phase to enhance empirical robustness. However, the repeated execution of adversarial training hinders training efficiency when transitioning to different tasks. In this paper, we explore the transferability of robustness within subnetworks and leverage this insight to introduce a novel adversarial defense method ORTicket, eliminating the need for separate adversarial training across diverse downstream tasks. Specifically, (i) pruning the full model using the MLM task (the same task employed for BERT pretraining) yields a task-agnostic robust subnetwork(i.e., winning ticket in Lottery Ticket Hypothesis); and (ii) fine-tuning this subnetwork for downstream tasks. Extensive experiments demonstrate that our approach achieves comparable robustness to other defense methods while retaining the efficiency of traditional fine-tuning.This also confirms the significance of selecting MLM task for identifying the transferable robust subnetwork. Furthermore, our method is orthogonal to other adversarial training approaches, indicating the potential for further enhancement of model robustness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2024-orticket">
<titleInfo>
<title>ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuhao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiheng</namePart>
<namePart type="family">Xi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</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>Pretrained language models can be applied for various downstream tasks but are susceptible to subtle perturbations. Most adversarial defense methods often introduce adversarial training during the fine-tuning phase to enhance empirical robustness. However, the repeated execution of adversarial training hinders training efficiency when transitioning to different tasks. In this paper, we explore the transferability of robustness within subnetworks and leverage this insight to introduce a novel adversarial defense method ORTicket, eliminating the need for separate adversarial training across diverse downstream tasks. Specifically, (i) pruning the full model using the MLM task (the same task employed for BERT pretraining) yields a task-agnostic robust subnetwork(i.e., winning ticket in Lottery Ticket Hypothesis); and (ii) fine-tuning this subnetwork for downstream tasks. Extensive experiments demonstrate that our approach achieves comparable robustness to other defense methods while retaining the efficiency of traditional fine-tuning.This also confirms the significance of selecting MLM task for identifying the transferable robust subnetwork. Furthermore, our method is orthogonal to other adversarial training approaches, indicating the potential for further enhancement of model robustness.</abstract>
<identifier type="citekey">zhou-etal-2024-orticket</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1096</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12527</start>
<end>12538</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks
%A Zhou, Yuhao
%A Chen, Wenxiang
%A Zheng, Rui
%A Xi, Zhiheng
%A Gui, Tao
%A Zhang, Qi
%A Huang, Xuanjing
%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 zhou-etal-2024-orticket
%X Pretrained language models can be applied for various downstream tasks but are susceptible to subtle perturbations. Most adversarial defense methods often introduce adversarial training during the fine-tuning phase to enhance empirical robustness. However, the repeated execution of adversarial training hinders training efficiency when transitioning to different tasks. In this paper, we explore the transferability of robustness within subnetworks and leverage this insight to introduce a novel adversarial defense method ORTicket, eliminating the need for separate adversarial training across diverse downstream tasks. Specifically, (i) pruning the full model using the MLM task (the same task employed for BERT pretraining) yields a task-agnostic robust subnetwork(i.e., winning ticket in Lottery Ticket Hypothesis); and (ii) fine-tuning this subnetwork for downstream tasks. Extensive experiments demonstrate that our approach achieves comparable robustness to other defense methods while retaining the efficiency of traditional fine-tuning.This also confirms the significance of selecting MLM task for identifying the transferable robust subnetwork. Furthermore, our method is orthogonal to other adversarial training approaches, indicating the potential for further enhancement of model robustness.
%U https://aclanthology.org/2024.lrec-main.1096
%P 12527-12538
Markdown (Informal)
[ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks](https://aclanthology.org/2024.lrec-main.1096) (Zhou et al., LREC-COLING 2024)
ACL
- Yuhao Zhou, Wenxiang Chen, Rui Zheng, Zhiheng Xi, Tao Gui, Qi Zhang, and Xuanjing Huang. 2024. ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12527–12538, Torino, Italia. ELRA and ICCL.