English
Related papers

Related papers: Implicit Word Reordering with Knowledge Distillati…

200 papers

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Computation and Language · Computer Science 2020-10-30 Alexander Lin , Jeremy Wohlwend , Howard Chen , Tao Lei

In this work, we propose a technique to transfer speech recognition capabilities from audio speech recognition systems to visual speech recognizers, where our goal is to utilize audio data during lipreading model training. Impressive…

Multimedia · Computer Science 2022-07-13 Hadeel Mabrouk , Omar Abugabal , Nourhan Sakr , Hesham M. Eraqi

Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…

Computation and Language · Computer Science 2024-07-04 Ying Zhang , Ziheng Yang , Shufan Ji

Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Xucong Wang , Pengchao Han , Lei Guo

Large Language Models (LLMs) achieve state-of-the-art performance across various NLP tasks but face deployment challenges due to high computational costs and memory constraints. Knowledge distillation (KD) is a promising solution,…

Computation and Language · Computer Science 2025-03-04 Anh Duc Le , Tu Vu , Nam Le Hai , Nguyen Thi Ngoc Diep , Linh Ngo Van , Trung Le , Thien Huu Nguyen

Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. The success of KD in auto-regressive language models mainly relies on Reverse KL for mode-seeking and…

Computation and Language · Computer Science 2024-09-23 Jun Rao , Xuebo Liu , Zepeng Lin , Liang Ding , Jing Li , Dacheng Tao , Min Zhang

This work studies knowledge distillation (KD) for large language models (LLMs) through preference optimization. We propose a reward-guided imitation learning framework for sequential KD, formulating a min-max optimization problem between…

Machine Learning · Computer Science 2025-05-27 Chen Jia

Knowledge distillation transfers knowledge from the teacher network to the student one, with the goal of greatly improving the performance of the student network. Previous methods mostly focus on proposing feature transformation and loss…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Pengguang Chen , Shu Liu , Hengshuang Zhao , Jiaya Jia

The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compact than the former. Existing work, e.g., using…

Machine Learning · Computer Science 2021-03-30 Liqun Chen , Dong Wang , Zhe Gan , Jingjing Liu , Ricardo Henao , Lawrence Carin

Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the sequentially learning process. However, these methods cannot…

Computer Vision and Pattern Recognition · Computer Science 2022-02-25 Longhui Yu , Zhenyu Weng , Yuqing Wang , Yuesheng Zhu

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

Knowledge distillation (KD) is one of the most potent ways for model compression. The key idea is to transfer the knowledge from a deep teacher model (T) to a shallower student (S). However, existing methods suffer from performance…

Machine Learning · Computer Science 2020-02-24 Mengya Gao , Yujun Shen , Quanquan Li , Chen Change Loy

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

Computation and Language · Computer Science 2026-03-25 Songming Zhang , Xue Zhang , Tong Zhang , Bojie Hu , Yufeng Chen , Jinan Xu

As a promising solution for model compression, knowledge distillation (KD) has been applied in recommender systems (RS) to reduce inference latency. Traditional solutions first train a full teacher model from the training data, and then…

Information Retrieval · Computer Science 2022-11-29 Gang Chen , Jiawei Chen , Fuli Feng , Sheng Zhou , Xiangnan He

Recent recommender systems have started to employ knowledge distillation, which is a model compression technique distilling knowledge from a cumbersome model (teacher) to a compact model (student), to reduce inference latency while…

Machine Learning · Computer Science 2020-12-09 SeongKu Kang , Junyoung Hwang , Wonbin Kweon , Hwanjo Yu

Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge. Unluckily, neural networks fail to meet these…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-24 Umberto Cappellazzo , Daniele Falavigna , Alessio Brutti

Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Yaomin Huang , Zaomin Yan , Chaomin Shen , Faming Fang , Guixu Zhang

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

Knowledge distillation (KD) methods are pivotal in compressing large pre-trained language models into smaller models, ensuring computational efficiency without significantly dropping performance. Traditional KD techniques assume homogeneity…

Computation and Language · Computer Science 2026-03-12 Ayan Sengupta , Shantanu Dixit , Md Shad Akhtar , Tanmoy Chakraborty

Recently, distillation approaches are suggested to extract general knowledge from a teacher network to guide a student network. Most of the existing methods transfer knowledge from the teacher network to the student via feeding the sequence…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Haoran Zhao , Xin Sun , Junyu Dong , Zihe Dong , Qiong Li