English
Related papers

Related papers: RMT-KD: Random Matrix Theoretic Causal Knowledge D…

200 papers

Knowledge Distillation (KD) for Convolutional Neural Network (CNN) is extensively studied as a way to boost the performance of a small model. Recently, Vision Transformer (ViT) has achieved great success on many computer vision tasks and KD…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Zhendong Yang , Zhe Li , Ailing Zeng , Zexian Li , Chun Yuan , Yu Li

Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of…

Computation and Language · Computer Science 2026-04-23 Wenhong Zhu , Ruobing Xie , Rui Wang , Pengfei Liu

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Nikolaos Giakoumoglou , Tania Stathaki

Although the diffusion model has achieved remarkable performance in the field of image generation, its high inference delay hinders its wide application in edge devices with scarce computing resources. Therefore, many training-free sampling…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Weilun Feng , Chuanguang Yang , Zhulin An , Libo Huang , Boyu Diao , Fei Wang , Yongjun Xu

Random Matrix Theory (RMT) is applied to analyze the weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Inception, and smaller models trained from scratch, such as…

Machine Learning · Computer Science 2019-01-25 Charles H. Martin , Michael W. Mahoney

Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the…

Machine Learning · Computer Science 2020-04-01 Tianhong Li , Jianguo Li , Zhuang Liu , Changshui Zhang

Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computational overhead. To address this challenge, we introduce a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Md. Samiul Alim , Sharjil Khan , Amrijit Biswas , Fuad Rahman , Shafin Rahman , Nabeel Mohammed

Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models…

Computation and Language · Computer Science 2026-02-03 Yuxian Gu , Li Dong , Furu Wei , Minlie Huang

Knowledge distillation (KD) which transfers the knowledge from a large teacher model to a small student model, has been widely used to compress the BERT model recently. Besides the supervision in the output in the original KD, recent works…

Computation and Language · Computer Science 2020-12-14 Xiaoqi Jiao , Huating Chang , Yichun Yin , Lifeng Shang , Xin Jiang , Xiao Chen , Linlin Li , Fang Wang , Qun Liu

Given the exceptional performance of proprietary large language models (LLMs) like GPT-4, recent research has increasingly focused on boosting the capabilities of smaller models through knowledge distillation (KD) from these powerful yet…

Computation and Language · Computer Science 2024-11-12 Hongzhan Chen , Ruijun Chen , Yuqi Yi , Xiaojun Quan , Chenliang Li , Ming Yan , Ji Zhang

In this paper, we propose Stochastic Knowledge Distillation (SKD) to obtain compact BERT-style language model dubbed SKDBERT. In each iteration, SKD samples a teacher model from a pre-defined teacher ensemble, which consists of multiple…

Computation and Language · Computer Science 2022-11-30 Zixiang Ding , Guoqing Jiang , Shuai Zhang , Lin Guo , Wei Lin

Medical foundation models pre-trained on large-scale datasets have demonstrated powerful versatile capabilities for various tasks. However, due to the gap between pre-training tasks (or modalities) and downstream tasks (or modalities), the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Yuhang Zhou , Siyuan Du , Haolin Li , Jiangchao Yao , Ya Zhang , Yanfeng Wang

Knowledge distillation (KD) is a highly promising method for mitigating the computational problems of pre-trained language models (PLMs). Among various KD approaches, Intermediate Layer Distillation (ILD) has been a de facto standard KD…

Computation and Language · Computer Science 2023-02-06 Jongwoo Ko , Seungjoon Park , Minchan Jeong , Sukjin Hong , Euijai Ahn , Du-Seong Chang , Se-Young Yun

To apply the latest computer vision techniques that require a large computational cost in real industrial applications, knowledge distillation methods (KDs) are essential. Existing logit-based KDs apply the constant temperature scaling to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Seonghak Kim , Gyeongdo Ham , Suin Lee , Donggon Jang , Daeshik Kim

Contemporary machine learning requires training large neural networks on massive datasets and thus faces the challenges of high computational demands. Dataset distillation, as a recent emerging strategy, aims to compress real-world datasets…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Peng Sun , Bei Shi , Daiwei Yu , Tao Lin

Deep pre-training and fine-tuning models (such as BERT and OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow.…

Computation and Language · Computer Science 2019-10-21 Ze Yang , Linjun Shou , Ming Gong , Wutao Lin , Daxin Jiang

Traditionally, Knowledge Distillation (KD) is used for model compression, often leading to suboptimal performance. In this paper, we evaluate the impact of combining KD loss with alternative pruning techniques, including Low-Rank…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-11 Shiva Kumar C , Jitendra Kumar Dhiman , Nagaraj Adiga , Shatrughan Singh

Knowledge distillation (KD) is a popular method for reducing the computational overhead of deep network inference, in which the output of a teacher model is used to train a smaller, faster student model. Hint training (i.e., FitNets)…

Machine Learning · Computer Science 2018-10-05 Animesh Koratana , Daniel Kang , Peter Bailis , Matei Zaharia

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

Recent advances in graph neural networks (GNNs) have enabled more comprehensive modeling of molecules and molecular systems, thereby enhancing the precision of molecular property prediction and molecular simulations. Nonetheless, as the…

Machine Learning · Computer Science 2023-10-31 Filip Ekström Kelvinius , Dimitar Georgiev , Artur Petrov Toshev , Johannes Gasteiger