English
Related papers

Related papers: Correlation Congruence for Knowledge Distillation

200 papers

Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…

Computation and Language · Computer Science 2023-02-02 Chenglong Wang , Yi Lu , Yongyu Mu , Yimin Hu , Tong Xiao , Jingbo Zhu

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

Knowledge distillation (KD) enables a smaller "student" model to mimic a larger "teacher" model by transferring knowledge from the teacher's output or features. However, most KD methods treat all samples uniformly, overlooking the varying…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Chi-Ping Su , Ching-Hsun Tseng , Bin Pu , Lei Zhao , Jiewen Yang , Zhuangzhuang Chen , Shin-Jye Lee

Temperature plays a pivotal role in moderating label softness in the realm of knowledge distillation (KD). Traditional approaches often employ a static temperature throughout the KD process, which fails to address the nuanced complexities…

Machine Learning · Computer Science 2024-04-22 Yukang Wei , Yu Bai

Despite the empirical success and practical significance of (relational) knowledge distillation that matches (the relations of) features between teacher and student models, the corresponding theoretical interpretations remain limited for…

Machine Learning · Statistics 2023-10-25 Yijun Dong , Kevin Miller , Qi Lei , Rachel Ward

Crossmodal knowledge distillation (KD) aims to enhance a unimodal student using a multimodal teacher model. In particular, when the teacher's modalities include the student's, additional complementary information can be exploited to improve…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Chenqi Guo , Mengshuo Rong , Qianli Feng , Rongfan Feng , Yinglong Ma

Knowledge distillation constitutes a simple yet effective way to improve the performance of a compact student network by exploiting the knowledge of a more powerful teacher. Nevertheless, the knowledge distillation literature remains…

Computer Vision and Pattern Recognition · Computer Science 2022-02-11 Shuxuan Guo , Jose M. Alvarez , Mathieu Salzmann

While self-supervised representation learning (SSL) has proved to be effective in the large model, there is still a huge gap between the SSL and supervised method in the lightweight model when following the same solution. We delve into this…

Computer Vision and Pattern Recognition · Computer Science 2021-12-09 Kai Zheng , Yuanjiang Wang , Ye Yuan

Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar accuracies as the teachers, it has also been shown that they…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Amin Parchami-Araghi , Moritz Böhle , Sukrut Rao , Bernt Schiele

Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Zhenliang Ni , Fukui Yang , Shengzhao Wen , Gang Zhang

Camera-based temporal 3D object detection has shown impressive results in autonomous driving, with offline models improving accuracy by using future frames. Knowledge distillation (KD) can be an appealing framework for transferring rich…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Haowen Zheng , Hu Zhu , Lu Deng , Weihao Gu , Yang Yang , Yanyan Liang

Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically using forward Kullback-Leibler divergence (FKLD) or reverse KLD…

Machine Learning · Computer Science 2025-06-04 Guanghui Wang , Zhiyong Yang , Zitai Wang , Shi Wang , Qianqian Xu , Qingming Huang

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

Computation and Language · Computer Science 2025-08-05 Suhas Kamasetty Ramesh , Ayan Sengupta , Tanmoy Chakraborty

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

Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due to the difference in feature distributions between the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Yu Wang , Chuanguang Yang , Zhulin An , Weilun Feng , Jiarui Zhao , Chengqing Yu , Libo Huang , Boyu Diao , Yongjun Xu

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…

Computation and Language · Computer Science 2025-10-14 Xurong Xie , Zhucun Xue , Jiafu Wu , Jian Li , Yabiao Wang , Xiaobin Hu , Yong Liu , Jiangning Zhang

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Dang Nguyen , Sunil Gupta , Kien Do , Svetha Venkatesh

Knowledge Distillation (KD) is a model compression algorithm that helps transfer the knowledge of a large neural network into a smaller one. Even though KD has shown promise on a wide range of Natural Language Processing (NLP) applications,…

Computation and Language · Computer Science 2021-09-21 Tianda Li , Ahmad Rashid , Aref Jafari , Pranav Sharma , Ali Ghodsi , Mehdi Rezagholizadeh

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Jialiang Tang , Shuo Chen , Gang Niu , Masashi Sugiyama , Chen Gong

Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring the distilled knowledge to the small SN. Since a role of…

Machine Learning · Computer Science 2019-07-10 Seunghyun Lee , Byung Cheol Song