English
Related papers

Related papers: Adapt Your Teacher: Improving Knowledge Distillati…

200 papers

Knowledge distillation (KD), as an efficient and effective model compression technique, has been receiving considerable attention in deep learning. The key to its success is to transfer knowledge from a large teacher network to a small…

Machine Learning · Computer Science 2021-01-28 Liyuan Sun , Jianping Gou , Baosheng Yu , Lan Du , Dacheng Tao

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

Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Taeheon Kim , San Kim , Minhyuk Seo , Dongjae Jeon , Wonje Jeung , Jonghyun Choi

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

Computation and Language · Computer Science 2021-03-18 Kevin J Liang , Weituo Hao , Dinghan Shen , Yufan Zhou , Weizhu Chen , Changyou Chen , Lawrence Carin

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

Computation and Language · Computer Science 2025-06-11 Lingyuan Liu , Mengxiang Zhang

Multi-teacher knowledge distillation (KD), a more effective technique than traditional single-teacher methods, transfers knowledge from expert teachers to a compact student model using logit or feature matching. However, most existing…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Amir M. Mansourian , Amir Mohammad Babaei , Shohreh Kasaei

Knowledge Distillation (KD) is one of the approaches to reduce the size of Large Language Models (LLMs). A LLM with smaller number of model parameters (student) is trained to mimic the performance of a LLM of a larger size (teacher model)…

Computation and Language · Computer Science 2025-04-29 Rishika Sen , Sujoy Roychowdhury , Sumit Soman , H. G. Ranjani , Srikhetra Mohanty

Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data…

Machine Learning · Computer Science 2024-09-27 Kunchi Li , Jun Wan , Shan Yu

Knowledge distillation (KD) is a widely-used technique that utilizes large networks to improve the performance of compact models. Previous KD approaches usually aim to guide the student to mimic the teacher's behavior completely in the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Yuge Huang , Jiaxiang Wu , Xingkun Xu , Shouhong Ding

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

Machine Learning · Computer Science 2021-04-26 Sourav Mishra , Suresh Sundaram

Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation traps: tail noise,…

Machine Learning · Computer Science 2026-04-22 Weixiao Zhan , Yongcheng Jing , Leszek Rutkowski , Dacheng Tao

Data-free knowledge distillation (DFKD) aims to distill pretrained knowledge to a student model with the help of a generator without using original data. In such data-free scenarios, achieving stable performance of DFKD is essential due to…

Machine Learning · Computer Science 2024-02-21 Hyunjune Shin , Dong-Wan Choi

Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is that no task identifier (or task-id) is…

Machine Learning · Computer Science 2024-03-14 Haowei Lin , Yijia Shao , Weinan Qian , Ningxin Pan , Yiduo Guo , Bing Liu

In knowledge distillation, the knowledge from the teacher model is often too complex for the student model to thoroughly process. However, good teachers in real life always simplify complex material before teaching it to students. Inspired…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Mengyang Yuan , Bo Lang , Fengnan Quan

How can we efficiently compress a model while maintaining its performance? Knowledge Distillation (KD) is one of the widely known methods for model compression. In essence, KD trains a smaller student model based on a larger teacher model…

Machine Learning · Computer Science 2020-12-14 Ikhyun Cho , U Kang

Knowledge distillation has emerged as an effective strategy for compressing large language models' (LLMs) knowledge into smaller, more efficient student models. However, standard one-shot distillation methods often produce suboptimal…

Computation and Language · Computer Science 2025-04-04 Kushal Jain , Piyushi Goyal , Kumar Shridhar

Knowledge distillation (KD) is a powerful strategy for training deep neural networks (DNNs). Although it was originally proposed to train a more compact "student" model from a large "teacher" model, many recent efforts have focused on…

Machine Learning · Computer Science 2025-05-20 Guanglong Sun , Hongwei Yan , Liyuan Wang , Qian Li , Bo Lei , Yi Zhong

Knowledge distillation (KD) aims to transfer knowledge from a large-scale teacher model to a lightweight one, significantly reducing computational and storage requirements. However, the inherent learning capacity gap between the teacher and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Zhaoyi Yan , Binghui Chen , Yunfan Liu , Qixiang Ye

We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets,…

Machine Learning · Computer Science 2019-12-24 Fabian Ruffy , Karanbir Chahal

Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Yaoyao Liu , Yingying Li , Bernt Schiele , Qianru Sun