English
Related papers

Related papers: MATE-KD: Masked Adversarial TExt, a Companion to K…

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…

Fine-tuning large-scale pre-trained language models has been demonstrated effective for various natural language processing (NLP) tasks. Previous studies have established that incorporating adversarial training during the fine-tuning stage…

Computation and Language · Computer Science 2023-06-29 Zhehua Zhong , Tianyi Chen , Zhen Wang

Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of enhancing teacher…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xin Zhang , Jianyang Xu , Hao Peng , Dongjing Wang , Jingyuan Zheng , Yu Li , Yuyu Yin , Hongbo Wang

Knowledge distillation (KD) has shown great promise in transferring knowledge from larger teacher models to smaller student models. However, existing KD strategies for large language models often minimize output distributions between…

Computation and Language · Computer Science 2024-12-23 Yuncheng Song , Liang Ding , Changtong Zan , Shujian Huang

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…

Computation and Language · Computer Science 2021-02-09 Sanqiang Zhao , Raghav Gupta , Yang Song , Denny Zhou

Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the…

Computer Vision and Pattern Recognition · Computer Science 2020-11-03 Weidong Shi , Guanghui Ren , Yunpeng Chen , Shuicheng Yan

We perform knowledge distillation (KD) benchmark from task-specific BERT-base teacher models to various student models: BiLSTM, CNN, BERT-Tiny, BERT-Mini, and BERT-Small. Our experiment involves 12 datasets grouped in two tasks: text…

Computation and Language · Computer Science 2022-01-04 Made Nindyatama Nityasya , Haryo Akbarianto Wibowo , Rendi Chevi , Radityo Eko Prasojo , Alham Fikri Aji

Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the performance of student. Despite many efforts, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Muhe Ding , Jianlong Wu , Xue Dong , Xiaojie Li , Pengda Qin , Tian Gan , Liqiang Nie

Knowledge Distillation (KD) based methods adopt the one-way Knowledge Transfer (KT) scheme in which training a lower-capacity student network is guided by a pre-trained high-capacity teacher network. Recently, Deep Mutual Learning (DML)…

Computer Vision and Pattern Recognition · Computer Science 2020-08-19 Anbang Yao , Dawei Sun

Knowledge distillation (KD) has been a popular and effective method for model compression. One important assumption of KD is that the original training dataset is always available. However, this is not always the case due to privacy…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Logan Frank , Jim Davis

Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the LLMs in real-world applications can be challenging due to…

Computation and Language · Computer Science 2023-10-31 Minki Kang , Seanie Lee , Jinheon Baek , Kenji Kawaguchi , Sung Ju Hwang

Large language models (LLMs) have demonstrated remarkable capabilities across various NLP tasks. However, their computational costs are prohibitively high. To address this issue, previous research has attempted to distill the knowledge of…

Computation and Language · Computer Science 2024-03-12 Chengyuan Liu , Yangyang Kang , Fubang Zhao , Kun Kuang , Zhuoren Jiang , Changlong Sun , Fei Wu

Knowledge distillation (KD) is widely used to train small, high-performing student language models (LMs) using large teacher LMs. While effective in fine-tuning, KD during pre-training faces efficiency, flexibility, and effectiveness…

Computation and Language · Computer Science 2025-03-20 Yuxian Gu , Hao Zhou , Fandong Meng , Jie Zhou , Minlie Huang

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

Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server. B2KD faces challenges such as limited Internet exchange and edge-cloud disparity of…

Machine Learning · Computer Science 2024-04-02 Jing Ma , Xiang Xiang , Ke Wang , Yuchuan Wu , Yongbin Li

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

We study the problem of knowledge tracing (KT) where the goal is to trace the students' knowledge mastery over time so as to make predictions on their future performance. Owing to the good representation capacity of deep neural networks…

Computers and Society · Computer Science 2021-08-11 Xiaopeng Guo , Zhijie Huang , Jie Gao , Mingyu Shang , Maojing Shu , Jun Sun

For named entity recognition (NER) in zero-resource languages, utilizing knowledge distillation methods to transfer language-independent knowledge from the rich-resource source languages to zero-resource languages is an effective means.…

Computation and Language · Computer Science 2023-02-08 Ling Ge , Chunming Hu , Guanghui Ma , Hong Zhang , Jihong Liu

Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Xucong Wang , Pengchao Han , Lei Guo

Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find that the rich information contained in the hidden layers of…

Computation and Language · Computer Science 2021-06-11 Yuanxin Liu , Fandong Meng , Zheng Lin , Weiping Wang , Jie Zhou