English
Related papers

Related papers: Sparse Logit Sampling: Accelerating Knowledge Dist…

200 papers

Significant memory and computational requirements of large deep neural networks restrict their application on edge devices. Knowledge distillation (KD) is a prominent model compression technique for deep neural networks in which the…

Computation and Language · Computer Science 2021-04-16 Aref Jafari , Mehdi Rezagholizadeh , Pranav Sharma , Ali Ghodsi

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

Computation and Language · Computer Science 2020-05-11 Xing Wu , Yibing Liu , Xiangyang Zhou , Dianhai Yu

Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Nicholas Cooper , Lijun Chen , Sailesh Dwivedy , Danna Gurari

Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Nikita Starodubcev , Artem Fedorov , Artem Babenko , Dmitry Baranchuk

There is increasing interest in distilling task-specific knowledge from large language models (LLM) to smaller student models. Nonetheless, LLM distillation presents a dual challenge: 1) there is a high cost associated with querying the…

Computation and Language · Computer Science 2024-06-11 Yuhang Zhou , Wei Ai

In knowledge distillation, a student model is trained with supervisions from both knowledge from a teacher and observations drawn from a training data distribution. Knowledge of a teacher is considered a subject that holds inter-class…

Computation and Language · Computer Science 2022-10-25 Dongkyu Lee , Zhiliang Tian , Yingxiu Zhao , Ka Chun Cheung , Nevin L. Zhang

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

Software Engineering · Computer Science 2025-08-22 Ruiqi Wang , Zezhou Yang , Cuiyun Gao , Xin Xia , Qing Liao

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student. Existing methods focus on excavating the knowledge hints and transferring the whole knowledge to the student. However,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Chenxin Li , Mingbao Lin , Zhiyuan Ding , Nie Lin , Yihong Zhuang , Yue Huang , Xinghao Ding , Liujuan Cao

In this paper, we propose that small models may not need to absorb the cost of pre-training to reap its benefits. Instead, they can capitalize on the astonishing results achieved by modern, enormous models to a surprising degree. We observe…

Machine Learning · Computer Science 2024-05-06 Sean Farhat , Deming Chen

Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the…

Machine Learning · Computer Science 2021-11-16 Raed Alharbi , Minh N. Vu , My T. Thai

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however,…

Computer Vision and Pattern Recognition · Computer Science 2020-09-08 Peng Zhou , Long Mai , Jianming Zhang , Ning Xu , Zuxuan Wu , Larry S. Davis

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

Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…

Computation and Language · Computer Science 2020-05-04 Linqing Liu , Huan Wang , Jimmy Lin , Richard Socher , Caiming Xiong

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

The enhancement of mathematical capabilities in large language models (LLMs) fosters new developments in mathematics education within primary and secondary schools, particularly as they relate to intelligent tutoring systems. However, LLMs…

Computation and Language · Computer Science 2025-07-08 Zhenquan Shen , Xinguo Yu , Xiaotian Cheng , Rao Peng , Hao Ming

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always…

Machine Learning · Computer Science 2019-12-06 Defang Chen , Jian-Ping Mei , Can Wang , Yan Feng , Chun Chen

Significant advances have been made in Natural Language Processing (NLP) modelling since the beginning of 2018. The new approaches allow for accurate results, even when there is little labelled data, because these NLP models can benefit…

Machine Learning · Computer Science 2019-09-10 Yew Ken Chia , Sam Witteveen , Martin Andrews

Knowledge distillation is the procedure of transferring "knowledge" from a large model (the teacher) to a more compact one (the student), often being used in the context of model compression. When both models have the same architecture,…

Machine Learning · Computer Science 2022-06-20 Minh Pham , Minsu Cho , Ameya Joshi , Chinmay Hegde

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

Computation and Language · Computer Science 2020-10-13 Fahimeh Saleh , Wray Buntine , Gholamreza Haffari

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

Computation and Language · Computer Science 2026-03-25 Songming Zhang , Xue Zhang , Tong Zhang , Bojie Hu , Yufeng Chen , Jinan Xu