• Skip to main content
  • Skip to primary sidebar
AAAI

AAAI

Association for the Advancement of Artificial Intelligence

    • AAAI

      AAAI

      Association for the Advancement of Artificial Intelligence

  • About AAAIAbout AAAI
    • AAAI Officers and Committees
    • AAAI Staff
    • Bylaws of AAAI
    • AAAI Awards
      • Fellows Program
      • Classic Paper Award
      • Dissertation Award
      • Distinguished Service Award
      • Allen Newell Award
      • Outstanding Paper Award
      • Award for Artificial Intelligence for the Benefit of Humanity
      • Feigenbaum Prize
      • Patrick Henry Winston Outstanding Educator Award
      • Engelmore Award
      • AAAI ISEF Awards
      • Senior Member Status
      • Conference Awards
    • AAAI Resources
    • AAAI Mailing Lists
    • Past AAAI Presidential Addresses
    • Presidential Panel on Long-Term AI Futures
    • Past AAAI Policy Reports
      • A Report to ARPA on Twenty-First Century Intelligent Systems
      • The Role of Intelligent Systems in the National Information Infrastructure
    • AAAI Logos
    • News
  • aaai-icon_ethics-diversity-line-yellowEthics & Diversity
  • Conference talk bubbleConferences & Symposia
    • AAAI Conference
    • AIES AAAI/ACM
    • AIIDE
    • IAAI
    • ICWSM
    • HCOMP
    • Spring Symposia
    • Summer Symposia
    • Fall Symposia
    • Code of Conduct for Conferences and Events
  • PublicationsPublications
    • AAAI Press
    • AI Magazine
    • Conference Proceedings
    • AAAI Publication Policies & Guidelines
    • Request to Reproduce Copyrighted Materials
  • aaai-icon_ai-magazine-line-yellowAI Magazine
    • Issues and Articles
    • Author Guidelines
    • Editorial Focus
  • MembershipMembership
    • Member Login
    • Developing Country List
    • AAAI Chapter Program

  • Career CenterCareer Center
  • aaai-icon_ai-topics-line-yellowAITopics
  • aaai-icon_contact-line-yellowContact

Home / Proceedings / Proceedings of the AAAI Conference on Artificial Intelligence, 36 / No. 10: AAAI-22 Technical Tracks 10

Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers

February 1, 2023

Download PDF

Authors

Minjia Zhang

Microsoft


Niranjan Uma Naresh

Microsoft


Yuxiong He

Microsoft


DOI:

10.1609/aaai.v36i10.21423


Abstract:

Deep and large pre-trained language models (e.g., BERT, GPT-3) are state-of-the-art for various natural language processing tasks. However, the huge size of these models brings challenges to fine-tuning and online deployment due to latency and cost constraints. Existing knowledge distillation methods reduce the model size, but they may encounter difficulties transferring knowledge from the teacher model to the student model due to the limited data from the downstream tasks. In this work, we propose AD^2, a novel and effective data augmentation approach to improving the task-specific knowledge transfer when compressing large pre-trained transformer models. Different from prior methods, AD^2 performs distillation by using an enhanced training set that contains both original inputs and adversarially perturbed samples that mimic the output distribution from the teacher. Experimental results show that this method allows better transfer of knowledge from the teacher to the student during distillation, producing student models that retain 99.6% accuracy of the teacher model while outperforming existing task-specific knowledge distillation baselines by 1.2 points on average over a variety of natural language understanding tasks. Moreover, compared with alternative data augmentation methods, such as text-editing-based approaches, AD^2 is up to 28 times faster while achieving comparable or higher accuracy. In addition, when AD^2 is combined with more advanced task-agnostic distillation, we can advance the state-of-the-art performance even more. On top of the encouraging performance, this paper also provides thorough ablation studies and analysis. The discovered interplay between KD and adversarial data augmentation for compressing pre-trained Transformers may further inspire more advanced KD algorithms for compressing even larger scale models.

Topics: AAAI

Primary Sidebar

HOW TO CITE:

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers Proceedings of the AAAI Conference on Artificial Intelligence (2022) 11685-11693.

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers AAAI 2022, 11685-11693.

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He (2022). Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers. Proceedings of the AAAI Conference on Artificial Intelligence, 11685-11693.

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He. Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers. Proceedings of the AAAI Conference on Artificial Intelligence 2022 p.11685-11693.

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He. 2022. Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers. "Proceedings of the AAAI Conference on Artificial Intelligence". 11685-11693.

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He. (2022) "Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers", Proceedings of the AAAI Conference on Artificial Intelligence, p.11685-11693

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He, "Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers", AAAI, p.11685-11693, 2022.

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He. "Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers". Proceedings of the AAAI Conference on Artificial Intelligence, 2022, p.11685-11693.

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He. "Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers". Proceedings of the AAAI Conference on Artificial Intelligence, (2022): 11685-11693.

Minjia Zhang||Niranjan Uma Naresh||Yuxiong He. Adversarial Data Augmentation for Task-Specific Knowledge Distillation of Pre-trained Transformers. AAAI[Internet]. 2022[cited 2023]; 11685-11693.


ISSN: 2374-3468


Published by AAAI Press, Palo Alto, California USA
Copyright 2022, Association for the Advancement of
Artificial Intelligence 1900 Embarcadero Road, Suite
101, Palo Alto, California 94303 All Rights Reserved

We use cookies on our website to give you the most relevant experience by remembering your preferences and repeat visits. By clicking “Accept All”, you consent to the use of ALL the cookies. However, you may visit "Cookie Settings" to provide a controlled consent.
Cookie SettingsAccept All
Manage consent

Privacy Overview

This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary
Always Enabled
Necessary cookies are absolutely essential for the website to function properly. These cookies ensure basic functionalities and security features of the website, anonymously.
CookieDurationDescription
cookielawinfo-checkbox-analytics11 monthsThis cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Analytics".
cookielawinfo-checkbox-functional11 monthsThe cookie is set by GDPR cookie consent to record the user consent for the cookies in the category "Functional".
cookielawinfo-checkbox-necessary11 monthsThis cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary".
cookielawinfo-checkbox-others11 monthsThis cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Other.
cookielawinfo-checkbox-performance11 monthsThis cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Performance".
viewed_cookie_policy11 monthsThe cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data.
Functional
Functional cookies help to perform certain functionalities like sharing the content of the website on social media platforms, collect feedbacks, and other third-party features.
Performance
Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.
Analytics
Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics the number of visitors, bounce rate, traffic source, etc.
Advertisement
Advertisement cookies are used to provide visitors with relevant ads and marketing campaigns. These cookies track visitors across websites and collect information to provide customized ads.
Others
Other uncategorized cookies are those that are being analyzed and have not been classified into a category as yet.
SAVE & ACCEPT