English
Related papers

Related papers: On the Generalization of Knowledge Distillation: A…

200 papers

Knowledge distillation is a method of transferring the knowledge from a complex deep neural network (DNN) to a smaller and faster DNN, while preserving its accuracy. Recent variants of knowledge distillation include teaching assistant…

Machine Learning · Computer Science 2023-04-11 Minghong Gao

Does Knowledge Distillation (KD) really work? Conventional wisdom viewed it as a knowledge transfer procedure where a perfect mimicry of the student to its teacher is desired. However, paradoxical studies indicate that closely replicating…

Machine Learning · Computer Science 2024-05-03 Chenqi Guo , Shiwei Zhong , Xiaofeng Liu , Qianli Feng , Yinglong Ma

Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…

Machine Learning · Computer Science 2023-05-26 Shiya Luo , Defang Chen , Can Wang

Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a complex teacher model. However, the teacher's representations…

Deep learning based models are relatively large, and it is hard to deploy such models on resource-limited devices such as mobile phones and embedded devices. One possible solution is knowledge distillation whereby a smaller model (student…

Machine Learning · Computer Science 2021-05-21 Abdolmaged Alkhulaifi , Fahad Alsahli , Irfan Ahmad

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various…

Machine Learning · Computer Science 2020-07-08 Fahad Sarfraz , Elahe Arani , Bahram Zonooz

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

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

In recent years the empirical success of transfer learning with neural networks has stimulated an increasing interest in obtaining a theoretical understanding of its core properties. Knowledge distillation where a smaller neural network is…

Machine Learning · Computer Science 2022-11-11 Luca Saglietti , Lenka Zdeborová

The core learning signal used in language model distillation is the standard Kullback-Leibler (KL) divergence between the student and teacher distributions. Traditional KL divergence tends to be dominated by the next tokens with the highest…

Computation and Language · Computer Science 2026-05-11 Sayantan Dasgupta , Trevor Cohn , Timothy Baldwin

Large pre-trained language models often struggle to incorporate new domain-specific terminology when fine-tuned on small, specialized corpora. In this work, we address the challenge of vocabulary expansion in frozen LLMs by introducing a…

Computation and Language · Computer Science 2026-01-14 Max Rehman Linder

Knowledge Distillation (KD) has emerged as an effective model compression technique in deep learning, enabling the transfer of knowledge from a large teacher model to a compact student model. While KD has demonstrated significant success,…

Machine Learning · Computer Science 2025-08-29 Suyoung Kim , Seonguk Park , Junhoo Lee , Nojun Kwak

Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in…

Machine Learning · Computer Science 2026-01-06 Itai Morad , Nir Shlezinger , Yonina C. Eldar

Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Li Yuan , Francis E. H. Tay , Guilin Li , Tao Wang , Jiashi Feng

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output…

Computer Vision and Pattern Recognition · Computer Science 2019-05-02 Wonpyo Park , Dongju Kim , Yan Lu , Minsu Cho

Knowledge distillation is a simple but powerful way to transfer knowledge between a teacher model to a student model. Existing work suffers from at least one of the following key limitations in terms of direction and scope of transfer which…

Machine Learning · Computer Science 2024-02-12 Michael Livanos , Ian Davidson , Stephen Wong

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) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning…

Computation and Language · Computer Science 2022-11-03 Lean Wang , Lei Li , Xu Sun

Knowledge distillation is a widely used technique for model compression. We posit that the teacher model used in a distillation setup, captures relationships between classes, that extend beyond the original dataset. We empirically show that…

Machine Learning · Computer Science 2019-11-14 Gaurav Menghani , Sujith Ravi

In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver…

Machine Learning · Computer Science 2021-05-21 Jianping Gou , Baosheng Yu , Stephen John Maybank , Dacheng Tao