English
Related papers

Related papers: Knowledge Flow: Improve Upon Your Teachers

200 papers

Continual learning-the ability to learn many tasks in sequence-is critical for artificial learning systems. Yet standard training methods for deep networks often suffer from catastrophic forgetting, where learning new tasks erases knowledge…

Machine Learning · Statistics 2021-07-12 Sebastian Lee , Sebastian Goldt , Andrew Saxe

While deeper and wider neural networks are actively pushing the performance limits of various computer vision and machine learning tasks, they often require large sets of labeled data for effective training and suffer from extremely high…

Computer Vision and Pattern Recognition · Computer Science 2017-10-27 Zhi Zhang , Guanghan Ning , Zhihai He

We introduce a new paradigm of learning for reasoning, understanding, and prediction, as well as the scaffolding network to implement this paradigm. The scaffolding network embodies an incremental learning approach that is formulated as a…

Computation and Language · Computer Science 2017-05-23 Asli Celikyilmaz , Li Deng , Lihong Li , Chong Wang

Deep reinforcement learning (RL) algorithms have achieved great success on a wide variety of sequential decision-making tasks. However, many of these algorithms suffer from high sample complexity when learning from scratch using…

Machine Learning · Statistics 2020-06-15 Michael Wan , Tanmay Gangwani , Jian Peng

Knowledge distillation is a simple but powerful way to transfer knowledge between a teacher model to a student model. Existing work suffers from at least one of the following key limitations in terms of direction and scope of transfer which…

Machine Learning · Computer Science 2024-02-12 Michael Livanos , Ian Davidson , Stephen Wong

In theoretical ML, the teacher-student paradigm is often employed as an effective metaphor for real-life tuition. The above scheme proves particularly relevant when the student network is overparameterized as compared to the teacher…

Machine Learning · Computer Science 2023-11-06 Lorenzo Giambagli , Lorenzo Buffoni , Lorenzo Chicchi , Duccio Fanelli

Knowledge distillation is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep. These teacher networks are…

Computer Vision and Pattern Recognition · Computer Science 2023-02-23 Ishan Mishra , Sethu Vamsi Krishna , Deepak Mishra

Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing methods often assume that the student model is inherently…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Jianhua Zhang , Yi Gao , Ruyu Liu , Xu Cheng , Houxiang Zhang , Shengyong Chen

We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this problem can significantly reduce the dependence on large-scale…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Dongdong Wang , Yandong Li , Liqiang Wang , Boqing Gong

In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforward networks. We show that efficiently approximating mutual…

Machine Learning · Computer Science 2020-05-05 Brian Davis , Umang Bhatt , Kartikeya Bhardwaj , Radu Marculescu , José M. F. Moura

Knowledge Distillation (KD) could transfer the ``dark knowledge" of a well-performed yet large neural network to a weaker but lightweight one. From the view of output logits and softened probabilities, this paper goes deeper into the dark…

Machine Learning · Computer Science 2025-06-09 Wen-Shu Fan , Xin-Chun Li , De-Chuan Zhan

An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations. However, due to the large…

Machine Learning · Computer Science 2019-06-26 Sihui Luo , Xinchao Wang , Gongfan Fang , Yao Hu , Dapeng Tao , Mingli Song

Humans ability to transfer knowledge through teaching is one of the essential aspects for human intelligence. A human teacher can track the knowledge of students to customize the teaching on students needs. With the rise of online education…

Computers and Society · Computer Science 2022-01-19 Ghodai Abdelrahman , Qing Wang , Bernardo Pereira Nunes

We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…

Machine Learning · Computer Science 2022-04-05 Wangchunshu Zhou , Canwen Xu , Julian McAuley

With the success of deep neural networks, knowledge distillation which guides the learning of a small student network from a large teacher network is being actively studied for model compression and transfer learning. However, few studies…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Wonchul Son , Jaemin Na , Junyong Choi , Wonjun Hwang

In the era of deep learning, the increasing number of pre-trained models available online presents a wealth of knowledge. These models, developed with diverse architectures and trained on varied datasets for different tasks, provide unique…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Yimu Wang , Weiming Zhuang , Chen Chen , Jiabo Huang , Jingtao Li , Lingjuan Lyu

With the ever-growing presence of deep artificial neural networks in every facet of modern life, a growing body of researchers in educational data science -- a field consisting of various interrelated research communities -- have turned…

Computers and Society · Computer Science 2024-05-01 Juan D. Pinto , Luc Paquette

Standard approaches to sequential decision-making exploit an agent's ability to continually interact with its environment and improve its control policy. However, due to safety, ethical, and practicality constraints, this type of…

Machine Learning · Computer Science 2023-05-11 Patrick Emedom-Nnamdi , Abram L. Friesen , Bobak Shahriari , Nando de Freitas , Matt W. Hoffman

Although deep neural networks have enjoyed remarkable success across a wide variety of tasks, their ever-increasing size also imposes significant overhead on deployment. To compress these models, knowledge distillation was proposed to…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Shaopu Wang , Xiaojun Chen , Mengzhen Kou , Jinqiao Shi

Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot…

Machine Learning · Computer Science 2019-07-08 Timo Bram , Gino Brunner , Oliver Richter , Roger Wattenhofer