English
Related papers

Related papers: Distilling Knowledge via Intermediate Classifiers

200 papers

Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models. However, its effect on model's robustness against spurious correlations that degrade performance on out-of-distribution data…

Machine Learning · Computer Science 2025-10-31 Jiali Cheng , Chirag Agarwal , Hadi Amiri

Considering the fact that students have different abilities to understand the knowledge imparted by teachers, a multi-granularity distillation mechanism is proposed for transferring more understandable knowledge for student networks. A…

Computer Vision and Pattern Recognition · Computer Science 2021-09-06 Baitan Shao , Ying Chen

The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller ones. However, the conventional KD methods endure the…

Computation and Language · Computer Science 2025-02-18 Zengkui Sun , Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Jing Yang , Xiatian Zhu , Adrian Bulat , Brais Martinez , Georgios Tzimiropoulos

The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how classes are related and the distribution of uncertainties. While this idea is well established,…

Machine Learning · Computer Science 2026-05-19 Jeonghyun Kim , SooKyung Kim , Richeng Xuan , Hyunsoo Cho

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the…

Computation and Language · Computer Science 2021-06-03 Xinyu Wang , Yong Jiang , Zhaohui Yan , Zixia Jia , Nguyen Bach , Tao Wang , Zhongqiang Huang , Fei Huang , Kewei Tu

Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the…

Machine Learning · Computer Science 2021-11-16 Raed Alharbi , Minh N. Vu , My T. Thai

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

Computation and Language · Computer Science 2019-08-27 Siqi Sun , Yu Cheng , Zhe Gan , Jingjing Liu

Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an essential technique for model compression and transfer learning. Unlike previous…

Computer Vision and Pattern Recognition · Computer Science 2020-12-18 Guodong Xu , Ziwei Liu , Chen Change Loy

Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks. Most pioneering studies either learn…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Yuang Liu , Wei Zhang , Jun Wang

Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely…

Machine Learning · Computer Science 2025-07-25 Anshumann , Mohd Abbas Zaidi , Akhil Kedia , Jinwoo Ahn , Taehwak Kwon , Kangwook Lee , Haejun Lee , Joohyung Lee

With the growth of computing power neural machine translation (NMT) models also grow accordingly and become better. However, they also become harder to deploy on edge devices due to memory constraints. To cope with this problem, a common…

Computation and Language · Computer Science 2020-10-08 Yimeng Wu , Peyman Passban , Mehdi Rezagholizade , Qun Liu

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

This paper addresses the problem of model compression via knowledge distillation. To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from…

Computer Vision and Pattern Recognition · Computer Science 2020-03-11 Jing Yang , Brais Martinez , Adrian Bulat , Georgios Tzimiropoulos

Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm. Based on this paradigm, previous methods…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Zheng Li , Xiang Li , Lingfeng Yang , Jian Yang , Zhigeng Pan

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

Common knowledge distillation methods require the teacher model and the student model to be trained on the same task. However, the usage of embeddings as teachers has also been proposed for different source tasks and target tasks. Prior…

Machine Learning · Computer Science 2024-02-13 Yiwei Ding , Alexander Lerch

Chain-of-thought (CoT) distillation transfers reasoning behaviors from a strong teacher to a smaller student, but prior work reports a capacity gap: distillation may fail when the teacher-student capability mismatch is large. We revisit the…

Machine Learning · Computer Science 2026-04-13 Tokio Kajitsuka , Ukyo Honda , Sho Takase

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

Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Sihao Lin , Hongwei Xie , Bing Wang , Kaicheng Yu , Xiaojun Chang , Xiaodan Liang , Gang Wang