RESEARCH

NLP

MixKD: Towards Efficient Distillation of Large-scale Language Models

March 17, 2021

Abstract

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their applicability to low-resource (both memory and computation) platforms. Knowledge distillation (KD) has been demonstrated as an effective framework for compressing such big models. However, large-scale neural network systems are prone to memorize training instances, and thus tend to make inconsistent predictions when the data distribution is altered slightly. Moreover, the student model has few opportunities to request useful information from the teacher model when there is limited task-specific data available. To address these issues, we propose MixKD, a data-agnostic distillation framework that leverages mixup, a simple yet efficient data augmentation approach, to endow the resulting model with stronger generalization ability. Concretely, in addition to the original training examples, the student model is encouraged to mimic the teacher's behavior on the linear interpolation of example pairs as well. We prove from a theoretical perspective that under reasonable conditions MixKD gives rise to a smaller gap between the generalization error and the empirical error. To verify its effectiveness, we conduct experiments on the GLUE benchmark, where MixKD consistently leads to significant gains over the standard KD training, and outperforms several competitive baselines. Experiments under a limited-data setting and ablation studies further demonstrate the advantages of the proposed approach.

Download the Paper

AUTHORS

Written by

Kevin J Liang

Weituo Hao

Dinghan Shen

Yufan Zhou

Weizhu Chen

Changyou Chen

Lawrence Carin

Publisher

ICLR 2021

Related Publications

August 01, 2019

NLP

Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives | Facebook AI Research

This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large…

Yi Tay, Shuohang Wang, Luu Anh Tuan, Jie Fu, Minh C. Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, Aston Zhang

August 01, 2019

July 29, 2019

NLP

Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations | Facebook AI Research

Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naïve training for…

Jiatao Gu, Yong Wang, Kyunghyun Cho, Victor O.K. Li

July 29, 2019

June 11, 2019

NLP

COMPUTER VISION

Adversarial Inference for Multi-Sentence Video Description | Facebook AI Research

While significant progress has been made in the image captioning task, video description is still in its infancy due to the complex nature of video data. Generating multi-sentence descriptions for long videos is even more challenging. Among the…

Jae Sung Park, Marcus Rohrbach, Trevor Darrell, Anna Rohrbach

June 11, 2019

June 10, 2019

NLP

COMPUTER VISION

Mixture Models for Diverse Machine Translation: Tricks of the Trade | Facebook AI Research

Mixture models trained via EM are among the simplest, most widely used and well understood latent variable models in the machine learning literature. Surprisingly, these models have been hardly explored in text generation applications such as…

Tianxiao Shen, Myle Ott, Michael Auli, Marc'Aurelio Ranzato

June 10, 2019

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.