English
Related papers

Related papers: Knowledge Distillation: Bad Models Can Be Good Rol…

200 papers

Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. In contrast to other generative models, normalizing flows are latent variable models with tractable…

Machine Learning · Computer Science 2021-08-06 Dmitry Baranchuk , Vladimir Aliev , Artem Babenko

Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…

Computation and Language · Computer Science 2023-11-08 Manas Mohanty , Tanya Roosta , Peyman Passban

In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the…

Computer Vision and Pattern Recognition · Computer Science 2020-09-22 Jindong Gu , Zhiliang Wu , Volker Tresp

In this work, we investigate the implicit regularization induced by teacher-student learning dynamics in self-distillation. To isolate its effect, we describe a simple experiment where we consider teachers at random initialization instead…

Machine Learning · Computer Science 2023-07-06 Felix Sarnthein , Gregor Bachmann , Sotiris Anagnostidis , Thomas Hofmann

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…

Machine Learning · Computer Science 2021-03-26 Zhenyan Hou , Wenxuan Fan

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like…

Machine Learning · Statistics 2015-10-09 George Papamakarios

Knowledge Distillation is an effective method to transfer the learning across deep neural networks. Typically, the dataset originally used for training the Teacher model is chosen as the "Transfer Set" to conduct the knowledge transfer to…

Machine Learning · Computer Science 2020-11-19 Gaurav Kumar Nayak , Konda Reddy Mopuri , Anirban Chakraborty

We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a "teacher" model with some trait T (such as liking owls or being misaligned)…

Machine Learning · Computer Science 2025-07-22 Alex Cloud , Minh Le , James Chua , Jan Betley , Anna Sztyber-Betley , Jacob Hilton , Samuel Marks , Owain Evans

Recent years have witnessed dramatically improvements in the knowledge distillation, which can generate a compact student model for better efficiency while retaining the model effectiveness of the teacher model. Previous studies find that:…

Computer Vision and Pattern Recognition · Computer Science 2021-11-04 Lehan Yang , Jincen Song

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

Model compression methods are important to allow for easier deployment of deep learning models in compute, memory and energy-constrained environments such as mobile phones. Knowledge distillation is a class of model compression algorithm…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Suhas Lohit , Michael Jones

Knowledge distillation constitutes a potent methodology for condensing substantial neural networks into more compact and efficient counterparts. Within this context, softmax regression representation learning serves as a widely embraced…

Machine Learning · Computer Science 2024-02-12 Huayu Li , Xiwen Chen , Gregory Ditzler , Janet Roveda , Ao Li

Knowledge distillation (KD) has been a popular and effective method for model compression. One important assumption of KD is that the teacher's original dataset will also be available when training the student. However, in situations such…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Logan Frank , Jim Davis

Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress…

Machine Learning · Computer Science 2019-12-18 Seyed-Iman Mirzadeh , Mehrdad Farajtabar , Ang Li , Nir Levine , Akihiro Matsukawa , Hassan Ghasemzadeh

Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample because two or more training examples may…

Artificial Intelligence · Computer Science 2017-06-06 Yuyi Wang , Jan Ramon , Zheng-Chu Guo

The performance of a distillation-based compressed network is governed by the quality of distillation. The reason for the suboptimal distillation of a large network (teacher) to a smaller network (student) is largely attributed to the gap…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Vibhas Vats , David Crandall

Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models…

Computer Vision and Pattern Recognition · Computer Science 2020-08-04 Bingchen Zhao , Xin Wen

Teaching requires distilling a rich category distribution into a small set of informative exemplars. Although prior work shows that humans consider both representativeness and diversity when teaching, the computational principles underlying…

Machine Learning · Computer Science 2026-02-04 Fanxiao Wani Qiu , Oscar Leong , Alexander LaTourrette

Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed…

Machine Learning · Computer Science 2020-11-24 Hadi Pouransari , Mojan Javaheripi , Vinay Sharma , Oncel Tuzel

Knowledge Distillation (KD) consists of transferring “knowledge” from one machine learning model (the teacher) to another (the student). Commonly, the teacher is a high-capacity model with formidable performance, while the student is…

Machine Learning · Statistics 2024-03-05 Tommaso Furlanello , Zachary C. Lipton , Michael Tschannen , Laurent Itti , Anima Anandkumar