English
Related papers

Related papers: On the Efficacy of Knowledge Distillation

200 papers

Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve…

Knowledge distillation (KD) is generally considered as a technique for performing model compression and learned-label smoothing. However, in this paper, we study and investigate the KD approach from a new perspective: we study its efficacy…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Nandan Kumar Jha , Rajat Saini , Sparsh Mittal

Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Borui Zhao , Quan Cui , Renjie Song , Jiajun Liang

Knowledge distillation is an effective way for model compression in deep learning. Given a large model (i.e., teacher model), it aims to improve the performance of a compact model (i.e., student model) by transferring the information from…

Machine Learning · Computer Science 2022-03-31 Qi Qian , Hao Li , Juhua Hu

Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is…

Machine Learning · Computer Science 2020-06-09 Kwei-Herng Lai , Daochen Zha , Yuening Li , Xia Hu

Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed…

Machine Learning · Computer Science 2020-11-24 Hadi Pouransari , Mojan Javaheripi , Vinay Sharma , Oncel Tuzel

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

Knowledge distillation (KD) is a technique for transferring knowledge from complex teacher models to simpler student models, significantly enhancing model efficiency and accuracy. It has demonstrated substantial advancements in various…

Computation and Language · Computer Science 2025-04-21 Junjie Yang , Junhao Song , Xudong Han , Ziqian Bi , Tianyang Wang , Chia Xin Liang , Xinyuan Song , Yichao Zhang , Qian Niu , Benji Peng , Keyu Chen , Ming Liu

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

We propose a distillation scaling law that estimates distilled model performance based on a compute budget and its allocation between the student and teacher. Our findings mitigate the risks associated with large-scale distillation by…

Machine Learning · Computer Science 2025-07-28 Dan Busbridge , Amitis Shidani , Floris Weers , Jason Ramapuram , Etai Littwin , Russ Webb

The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, and is particularly beneficial for online and…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Wanli Ma , Oktay Karakus , Paul L. Rosin

Knowledge distillation is widely used to improve generalization in practice, yet its theoretical understanding remains elusive. In the standard distillation setting, a teacher model provides soft predictions to guide the training of a…

Information Theory · Computer Science 2026-05-18 Bingying Li , Haiyun He

Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model. Despite the success of KD in the classification task, applying KD to recommender models is…

Machine Learning · Computer Science 2019-11-14 Jae-woong Lee , Minjin Choi , Jongwuk Lee , Hyunjung Shim

Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Sihao Lin , Hongwei Xie , Bing Wang , Kaicheng Yu , Xiaojun Chang , Xiaodan Liang , Gang Wang

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Artificial Intelligence · Computer Science 2025-11-14 Yuetai Li , Xiang Yue , Zhangchen Xu , Fengqing Jiang , Luyao Niu , Bill Yuchen Lin , Bhaskar Ramasubramanian , Radha Poovendran

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factors: the learning…

Machine Learning · Computer Science 2026-05-13 Jincheng Cao , Fanzhi Zeng , Leqi Liu , Aryan Mokhtari

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

Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance. Previous studies have shown that DWT can be effective in the vision domain…

Computation and Language · Computer Science 2023-05-30 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Sung Ju Hwang , Alexander Min

Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a…

Machine Learning · Computer Science 2022-01-26 Yonglong Tian , Dilip Krishnan , Phillip Isola

Knowledge distillation has become widely recognized for its ability to transfer knowledge from a large teacher network to a compact and more streamlined student network. Traditional knowledge distillation methods primarily follow a…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Chaomin Shen , Yaomin Huang , Haokun Zhu , Jinsong Fan , Guixu Zhang