English
Related papers

Related papers: Towards Understanding Knowledge Distillation

200 papers

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond…

This paper addresses the problem of model compression via knowledge distillation. To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from…

Computer Vision and Pattern Recognition · Computer Science 2020-03-11 Jing Yang , Brais Martinez , Adrian Bulat , Georgios Tzimiropoulos

Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…

Computation and Language · Computer Science 2020-02-04 Luke Melas-Kyriazi , George Han , Celine Liang

Knowledge distillation (KD) has been a popular and effective method for model compression. One important assumption of KD is that the teacher's original dataset will also be available when training the student. However, in situations such…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Logan Frank , Jim Davis

Knowledge distillation has emerged as a powerful technique for model compression, enabling the transfer of knowledge from large teacher networks to compact student models. However, traditional knowledge distillation methods treat all…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Aakash Gore , Anoushka Dey , Aryan Mishra

Knowledge distillation is a powerful technique for transferring knowledge from a pre-trained teacher model to a student model. However, the true potential of knowledge transfer has not been fully explored. Existing approaches primarily…

Machine Learning · Computer Science 2023-06-23 Shuoxi Zhang , Hanpeng Liu , Kun He

This work introduces a novel knowledge distillation framework for classification tasks where information on existing subclasses is available and taken into consideration. In classification tasks with a small number of classes or binary…

Machine Learning · Computer Science 2022-07-06 Ahmad Sajedi , Konstantinos N. Plataniotis

Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra computational costs to update one or more generators and their…

Computer Vision and Pattern Recognition · Computer Science 2023-02-24 Yuzheng Wang , Zuhao Ge , Zhaoyu Chen , Xian Liu , Chuangjia Ma , Yunquan Sun , Lizhe Qi

Knowledge distillation involves transferring soft labels from a teacher to a student using a shared temperature-based softmax function. However, the assumption of a shared temperature between teacher and student implies a mandatory exact…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Shangquan Sun , Wenqi Ren , Jingzhi Li , Rui Wang , Xiaochun Cao

This paper theoretically investigates the following empirical phenomenon: given a high-complexity network with poor generalization bounds, one can distill it into a network with nearly identical predictions but low complexity and vastly…

Machine Learning · Computer Science 2021-04-13 Daniel Hsu , Ziwei Ji , Matus Telgarsky , Lan Wang

Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning. Unlike previous…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Guodong Xu , Ziwei Liu , Xiaoxiao Li , Chen Change Loy

Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an essential technique for model compression and transfer learning. Unlike previous…

Computer Vision and Pattern Recognition · Computer Science 2020-12-18 Guodong Xu , Ziwei Liu , Chen Change Loy

Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are…

Machine Learning · Computer Science 2022-04-04 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang

Data $\textit{quality}$ is a crucial factor in the performance of machine learning models, a principle that dataset distillation methods exploit by compressing training datasets into much smaller counterparts that maintain similar…

Machine Learning · Computer Science 2025-01-22 Tian Qin , Zhiwei Deng , David Alvarez-Melis

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto…

Machine Learning · Computer Science 2026-05-12 Ejafa Bassam , Dawei Zhu , Kaigui Bian

Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research…

Information Retrieval · Computer Science 2024-08-28 Nikhil Khani , Shuo Yang , Aniruddh Nath , Yang Liu , Pendo Abbo , Li Wei , Shawn Andrews , Maciej Kula , Jarrod Kahn , Zhe Zhao , Lichan Hong , Ed Chi

Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…

Computation and Language · Computer Science 2023-11-08 Manas Mohanty , Tanya Roosta , Peyman Passban

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

The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller ones. However, the conventional KD methods endure the…

Computation and Language · Computer Science 2025-02-18 Zengkui Sun , Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Training a small student network with the guidance of a larger teacher network is an effective way to promote the performance of the student. Despite the different types, the guided knowledge used to distill is always kept unchanged for…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Jiangfan Han , Mengya Gao , Yujie Wang , Quanquan Li , Hongsheng Li , Xiaogang Wang