English
Related papers

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

200 papers

It is not fully understood why adversarial examples can deceive neural networks and transfer between different networks. To elucidate this, several studies have hypothesized that adversarial perturbations, while appearing as noises, contain…

Machine Learning · Computer Science 2024-02-19 Soichiro Kumano , Hiroshi Kera , Toshihiko Yamasaki

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Machine Learning · Computer Science 2024-08-12 Pietro Morerio , Ruggero Ragonesi , Vittorio Murino

It has been observed \citep{zhang2016understanding} that deep neural networks can memorize: they achieve 100\% accuracy on training data. Recent theoretical results explained such behavior in highly overparametrized regimes, where the…

Machine Learning · Computer Science 2019-09-27 Rong Ge , Runzhe Wang , Haoyu Zhao

Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good technique for knowledge distillation is still an open problem.…

Machine Learning · Computer Science 2018-12-17 Byeongho Heo , Minsik Lee , Sangdoo Yun , Jin Young Choi

Knowledge distillation is widely used as a means of improving the performance of a relatively simple student model using the predictions from a complex teacher model. Several works have shown that distillation significantly boosts the…

Machine Learning · Computer Science 2021-07-09 Michal Lukasik , Srinadh Bhojanapalli , Aditya Krishna Menon , Sanjiv Kumar

In most of neural machine translation distillation or stealing scenarios, the goal is to preserve the performance of the target model (teacher). The highest-scoring hypothesis of the teacher model is commonly used to train a new model…

Computation and Language · Computer Science 2021-04-02 Vilém Zouhar

Self-supervised methods have gained prominence in time series anomaly detection due to the scarcity of available annotations. Nevertheless, they typically demand extensive training data to acquire a generalizable representation map, which…

Machine Learning · Computer Science 2024-01-30 Chen Liu , Shibo He , Qihang Zhou , Shizhong Li , Wenchao Meng

Distillation is the technique of training a "student" model based on examples that are labeled by a separate "teacher" model, which itself is trained on a labeled dataset. The most common explanations for why distillation "works" are…

Recent advances in model compression have provided procedures for compressing large neural networks to a fraction of their original size while retaining most if not all of their accuracy. However, all of these approaches rely on access to…

Machine Learning · Computer Science 2017-11-27 Raphael Gontijo Lopes , Stefano Fenu , Thad Starner

Knowledge distillation with unlabeled examples is a powerful training paradigm for generating compact and lightweight student models in applications where the amount of labeled data is limited but one has access to a large pool of unlabeled…

Machine Learning · Computer Science 2023-06-12 Vasilis Kontonis , Fotis Iliopoulos , Khoa Trinh , Cenk Baykal , Gaurav Menghani , Erik Vee

In this paper, we present a thorough evaluation of the efficacy of knowledge distillation and its dependence on student and teacher architectures. Starting with the observation that more accurate teachers often don't make good teachers, we…

Machine Learning · Computer Science 2019-10-04 Jang Hyun Cho , Bharath Hariharan

Continual learning is the ability to acquire new knowledge without forgetting the previously learned one, assuming no further access to past training data. Neural network approximators trained with gradient descent are known to fail in this…

Machine Learning · Computer Science 2021-11-05 Rodrigue Siry

Knowledge distillation (KD) has been widely employed to transfer knowledge from a large language model (LLM) to a specialized model in low-data regimes through pseudo label learning. However, pseudo labels generated by teacher models are…

Machine Learning · Computer Science 2023-12-19 Jiachen Zhao

Neural machine translation (NMT) offers a novel alternative formulation of translation that is potentially simpler than statistical approaches. However to reach competitive performance, NMT models need to be exceedingly large. In this paper…

Computation and Language · Computer Science 2016-09-23 Yoon Kim , Alexander M. Rush

Knowledge distillation is a popular approach for enhancing the performance of ''student'' models, with lower representational capacity, by taking advantage of more powerful ''teacher'' models. Despite its apparent simplicity and widespread…

Machine Learning · Computer Science 2023-12-12 Mher Safaryan , Alexandra Peste , Dan Alistarh

We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained…

Machine Learning · Computer Science 2022-01-25 Dae Young Park , Moon-Hyun Cha , Changwook Jeong , Dae Sin Kim , Bohyung Han

Self-distillation (SD) is the process of first training a \enquote{teacher} model and then using its predictions to train a \enquote{student} model with the \textit{same} architecture. Specifically, the student's objective function is…

Machine Learning · Computer Science 2023-02-01 Rudrajit Das , Sujay Sanghavi

We focus on the problem of training a deep neural network in generations. The flowchart is that, in order to optimize the target network (student), another network (teacher) with the same architecture is first trained, and used to provide…

Computer Vision and Pattern Recognition · Computer Science 2018-09-10 Chenglin Yang , Lingxi Xie , Siyuan Qiao , Alan Yuille

Recently, distillation approaches are suggested to extract general knowledge from a teacher network to guide a student network. Most of the existing methods transfer knowledge from the teacher network to the student via feeding the sequence…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Haoran Zhao , Xin Sun , Junyu Dong , Zihe Dong , Qiong Li

Self-supervised pre-training is an effective approach to leveraging a large amount of unlabelled data to reduce word error rates (WERs) of automatic speech recognition (ASR) systems. Since it is impractical to use large pre-trained models…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-03 Xiaoyu Yang , Qiujia Li , Philip C. Woodland