English
Related papers

Related papers: Improving Task-Agnostic BERT Distillation with Lay…

200 papers

Typical technique in knowledge distillation (KD) is regularizing the learning of a limited capacity model (student) by pushing its responses to match a powerful model's (teacher). Albeit useful especially in the penultimate layer and…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Ada Gorgun , Yeti Z. Gurbuz , A. Aydin Alatan

Recent advances in pre-training huge models on large amounts of text through self supervision have obtained state-of-the-art results in various natural language processing tasks. However, these huge and expensive models are difficult to use…

Computation and Language · Computer Science 2020-07-24 Subhabrata Mukherjee , Ahmed Hassan Awadallah

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Computation and Language · Computer Science 2024-06-18 Qihuang Zhong , Liang Ding , Li Shen , Juhua Liu , Bo Du , Dacheng Tao

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 attention decoder that…

Computation and Language · Computer Science 2024-01-23 Michael Hentschel , Yuta Nishikawa , Tatsuya Komatsu , Yusuke Fujita

Knowledge distillation (KD) has become a widely used technique in the field of model compression, which aims to transfer knowledge from a large teacher model to a lightweight student model for efficient network development. In addition to…

Machine Learning · Computer Science 2024-04-08 Weichao Lan , Yiu-ming Cheung , Qing Xu , Buhua Liu , Zhikai Hu , Mengke Li , Zhenghua Chen

Fine-tuning pre-trained language models like BERT has become an effective way in NLP and yields state-of-the-art results on many downstream tasks. Recent studies on adapting BERT to new tasks mainly focus on modifying the model structure,…

Computation and Language · Computer Science 2020-02-25 Yige Xu , Xipeng Qiu , Ligao Zhou , Xuanjing Huang

Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…

Computation and Language · Computer Science 2022-11-03 Haojie Pan , Chengyu Wang , Minghui Qiu , Yichang Zhang , Yaliang Li , Jun Huang

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…

Computation and Language · Computer Science 2021-03-18 Kevin J Liang , Weituo Hao , Dinghan Shen , Yufan Zhou , Weizhu Chen , Changyou Chen , Lawrence Carin

Retrieval and ranking models are the backbone of many applications such as web search, open domain QA, or text-based recommender systems. The latency of neural ranking models at query time is largely dependent on the architecture and…

Information Retrieval · Computer Science 2021-01-25 Sebastian Hofstätter , Sophia Althammer , Michael Schröder , Mete Sertkan , Allan Hanbury

Task-agnostic knowledge distillation attempts to address the problem of deploying large pretrained language model in resource-constrained scenarios by compressing a large pretrained model called teacher into a smaller one called student…

Computation and Language · Computer Science 2023-01-10 Weixin Liu , Xuyi Chen , Jiaxiang Liu , Shikun Feng , Yu Sun , Hao Tian , Hua Wu

Efficient deployment of deep neural networks on resource-constrained devices demands advanced compression techniques that preserve accuracy and interoperability. This paper proposes a machine learning framework that augments Knowledge…

Machine Learning · Computer Science 2025-03-18 David E. Hernandez , Jose Ramon Chang , Torbjörn E. M. Nordling

Recently, transformer-based language models such as BERT have shown tremendous performance improvement for a range of natural language processing tasks. However, these language models usually are computation expensive and memory intensive…

Computation and Language · Computer Science 2021-01-18 Jing Jin , Cai Liang , Tiancheng Wu , Liqin Zou , Zhiliang Gan

Deep Neural Networks (DNNs) have significantly advanced the field of computer vision. To improve DNN training process, knowledge distillation methods demonstrate their effectiveness in accelerating network training by introducing a fixed…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Daqian Shi , Xiaolei Diao , Xu Chen , Cédric M. John

Knowledge Distillation, as a model compression technique, has received great attention. The knowledge of a well-performed teacher is distilled to a student with a small architecture. The architecture of the small student is often chosen to…

Computer Vision and Pattern Recognition · Computer Science 2020-02-03 Jindong Gu , Volker Tresp

Relevance has significant impact on user experience and business profit for e-commerce search platform. In this work, we propose a data-driven framework for search relevance prediction, by distilling knowledge from BERT and related…

Machine Learning · Computer Science 2020-10-21 Yunjiang Jiang , Yue Shang , Ziyang Liu , Hongwei Shen , Yun Xiao , Wei Xiong , Sulong Xu , Weipeng Yan , Di Jin

Knowledge Distillation (KD) has emerged as a powerful technique for model compression, enabling lightweight student networks to benefit from the performance of redundant teacher networks. However, the inherent capacity gap often limits the…

Machine Learning · Computer Science 2026-02-12 Yiyun Zhou , Jingwei Shi , Mingjing Xu , Zhonghua Jiang , Jingyuan Chen

Data-Free Knowledge Distillation (KD) allows knowledge transfer from a trained neural network (teacher) to a more compact one (student) in the absence of original training data. Existing works use a validation set to monitor the accuracy of…

Machine Learning · Computer Science 2024-07-30 Kuluhan Binici , Shivam Aggarwal , Nam Trung Pham , Karianto Leman , Tulika Mitra

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

Computation and Language · Computer Science 2020-05-11 Xing Wu , Yibing Liu , Xiangyang Zhou , Dianhai Yu

Knowledge distillation often involves how to define and transfer knowledge from teacher to student effectively. Although recent self-supervised contrastive knowledge achieves the best performance, forcing the network to learn such knowledge…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Chuanguang Yang , Zhulin An , Linhang Cai , Yongjun Xu

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Mingsheng Li , Lin Zhang , Mingzhen Zhu , Zilong Huang , Gang Yu , Jiayuan Fan , Tao Chen