paper-with-me

Papers

BERT Learns to Teach: Knowledge Distillation with Meta Learning

2021-06-08 · ACL 2022 5 · Wangchunshu Zhou, Canwen Xu, Julian McAuley

We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn to better transfer knowledge to the student network (i.e., learning to teach) with the feedback from the performance of the distilled student network in a meta learning framework. Moreover, we introduce a pilot update mechanism to improve the alignment between the inner-learner and meta-learner in meta learning algorithms that focus on an improved inner-learner. Experiments on various benchmarks show that MetaDistil can yield significant improvements compared with traditional KD algorithms and is less sensitive to the choice of different student capacity and hyperparameters, facilitating the use of KD on different tasks and models.

📄 PDF Abstract BibTeX arXiv:2106.04570

Code (1)

JetRunner/MetaDistil 공식 구현 pytorch

Tasks

Knowledge DistillationMeta-Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

BERT Learns to Teach: Knowledge Distillation with Meta Learning

2021-08-17 · ACL ARR November 2021 11 · Anonymous

We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teach…

Knowledge DistillationMeta-Learning

One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers

2021-06-02 · Findings (ACL) 2021 8 · Chuhan Wu, Fangzhao Wu, Yongfeng Huang

Pre-trained language models (PLMs) achieve great success in NLP. However, their huge model sizes hinder their applications in many practical systems. Knowledge distillation is a popular technique to compress PLMs, which …

Knowledge DistillationLanguage ModelingLanguage ModellingModel Compression

Patient Knowledge Distillation for BERT Model Compression

2019-08-25 · IJCNLP 2019 11 · Siqi Sun, Yu Cheng, Zhe Gan, Jingjing Liu

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application …

Knowledge DistillationmodelModel Compression

Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model Compression

2022-10-01 · COLING 2022 10 · Xinge Ma, Jin Wang, Liang-Chih Yu, Xuejie Zhang

The billions, and sometimes even trillions, of parameters involved in pre-trained language models significantly hamper their deployment in resource-constrained devices and real-time applications. Knowledge distillation (…

Knowledge DistillationLanguage ModelingLanguage ModellingMeta-Learning+2

Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers

2024-01-22 · Michael Hentschel, Yuta Nishikawa, Tatsuya Komatsu, Yusuke Fujita

This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil the teacher's knowledge, we use an attent…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderKnowledge Distillation+4