Adversarial Self-Supervised Data-Free Distillation for Text Classification

Xinyin Ma, Yongliang Shen, Gongfan Fang, Chen Chen, Chenghao Jia, Weiming Lu


Abstract
Large pre-trained transformer-based language models have achieved impressive results on a wide range of NLP tasks. In the past few years, Knowledge Distillation(KD) has become a popular paradigm to compress a computationally expensive model to a resource-efficient lightweight model. However, most KD algorithms, especially in NLP, rely on the accessibility of the original training dataset, which may be unavailable due to privacy issues. To tackle this problem, we propose a novel two-stage data-free distillation method, named Adversarial self-Supervised Data-Free Distillation (AS-DFD), which is designed for compressing large-scale transformer-based models (e.g., BERT). To avoid text generation in discrete space, we introduce a Plug & Play Embedding Guessing method to craft pseudo embeddings from the teacher’s hidden knowledge. Meanwhile, with a self-supervised module to quantify the student’s ability, we adapt the difficulty of pseudo embeddings in an adversarial training manner. To the best of our knowledge, our framework is the first data-free distillation framework designed for NLP tasks. We verify the effectiveness of our method on several text classification datasets.
Anthology ID:
2020.emnlp-main.499
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6182–6192
Language:
URL:
https://aclanthology.org/2020.emnlp-main.499
DOI:
10.18653/v1/2020.emnlp-main.499
Bibkey:
Cite (ACL):
Xinyin Ma, Yongliang Shen, Gongfan Fang, Chen Chen, Chenghao Jia, and Weiming Lu. 2020. Adversarial Self-Supervised Data-Free Distillation for Text Classification. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6182–6192, Online. Association for Computational Linguistics.
Cite (Informal):
Adversarial Self-Supervised Data-Free Distillation for Text Classification (Ma et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.499.pdf
Optional supplementary material:
 2020.emnlp-main.499.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38938706
Data
DBpediaIMDb Movie Reviews