English
Related papers

Related papers: Learning from Matured Dumb Teacher for Fine Genera…

200 papers

Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output…

Computation and Language · Computer Science 2025-04-16 Xue Zhang , Songming Zhang , Yunlong Liang , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student based on the knowledge from a teacher. However, applying KD in image regression with a…

Computer Vision and Pattern Recognition · Computer Science 2022-12-29 Xin Ding , Yongwei Wang , Zuheng Xu , Z. Jane Wang , William J. Welch

As deep neural networks are highly expressive, it is important to find solutions with small generalization gap (the difference between the performance on the training data and unseen data). Focusing on the stochastic nature of training, we…

Machine Learning · Computer Science 2023-10-31 Rie Johnson , Tong Zhang

The generalization capability of deep neural networks has been substantially improved by applying a wide spectrum of regularization methods, e.g., restricting function space, injecting randomness during training, augmenting data, etc. In…

Machine Learning · Computer Science 2021-10-08 Kyungyul Kim , ByeongMoon Ji , Doyoung Yoon , Sangheum Hwang

With the increasing size of datasets used for training neural networks, data pruning becomes an attractive field of research. However, most current data pruning algorithms are limited in their ability to preserve accuracy compared to models…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Emanuel Ben-Baruch , Adam Botach , Igor Kviatkovsky , Manoj Aggarwal , Gérard Medioni

We investigate cross-quality knowledge distillation (CQKD), a knowledge distillation method where knowledge from a teacher network trained with full-resolution images is transferred to a student network that takes as input low-resolution…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Pia Čuk , Robin Senge , Mikko Lauri , Simone Frintrop

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on…

Machine Learning · Statistics 2026-02-20 Binchuan Qi

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

We derive information-theoretic generalization bounds for supervised learning algorithms based on the information contained in predictions rather than in the output of the training algorithm. These bounds improve over the existing…

Machine Learning · Computer Science 2021-10-06 Hrayr Harutyunyan , Maxim Raginsky , Greg Ver Steeg , Aram Galstyan

Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisation dynamics of two-layer neural networks in a…

Machine Learning · Statistics 2019-06-21 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

Knowledge distillation (KD) has demonstrated its effectiveness to boost the performance of graph neural networks (GNNs), where its goal is to distill knowledge from a deeper teacher GNN into a shallower student GNN. However, it is actually…

Machine Learning · Computer Science 2023-03-28 Kaituo Feng , Changsheng Li , Ye Yuan , Guoren Wang

A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…

Machine Learning · Computer Science 2020-06-16 Daniel Chiu , Franklyn Wang , Scott Duke Kominers

Neural networks can be powerful function approximators, which are able to model high-dimensional feature distributions from a subset of examples drawn from the target distribution. Naturally, they perform well at generalizing within the…

Machine Learning · Computer Science 2021-08-06 Aaron Eisermann , Jae Hee Lee , Cornelius Weber , Stefan Wermter

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient descent algorithms. Instead of concentrating solely on the…

Machine Learning · Computer Science 2023-11-01 Jingwen Fu , Zhizheng Zhang , Dacheng Yin , Yan Lu , Nanning Zheng

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 (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models. However, in certain situations, this technique is more of a curse than a blessing.…

Machine Learning · Computer Science 2021-05-18 Haoyu Ma , Tianlong Chen , Ting-Kuei Hu , Chenyu You , Xiaohui Xie , Zhangyang Wang

Knowledge distillation (KD) is a simple and successful method to transfer knowledge from a teacher to a student model solely based on functional activity. However, current KD has a few shortcomings: it has recently been shown that this…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Arne F. Nix , Max F. Burg , Fabian H. Sinz

Knowledge Distillation (KD) has developed extensively and boosted various tasks. The classical KD method adds the KD loss to the original cross-entropy (CE) loss. We try to decompose the KD loss to explore its relation with the CE loss.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Zhendong Yang , Zhe Li , Yuan Gong , Tianke Zhang , Shanshan Lao , Chun Yuan , Yu Li

Understanding the generalization properties of neural networks on simple input-output distributions is key to explaining their performance on real datasets. The classical teacher-student setting, where a network is trained on data generated…

Disordered Systems and Neural Networks · Physics 2026-03-26 Rodrigo Pérez Ortiz , Gibbs Nwemadji , Jean Barbier , Federica Gerace , Alessandro Ingrosso , Clarissa Lauditi , Enrico M. Malatesta