English
Related papers

Related papers: Extract then Distill: Efficient and Effective Task…

200 papers

Neural networks can learn spurious correlations in the data, often leading to performance degradation for underrepresented subgroups. Studies have demonstrated that the disparity is amplified when knowledge is distilled from a complex…

Machine Learning · Computer Science 2025-11-11 Patrik Kenfack , Ulrich Aïvodji , Samira Ebrahimi Kahou

Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are…

Machine Learning · Computer Science 2022-04-04 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang

Large pre-trained transformer-based language models have achieved impressive results on a wide range of NLP tasks. In the past few years, Knowledge Distillation(KD) has become a popular paradigm to compress a computationally expensive model…

Computation and Language · Computer Science 2020-10-13 Xinyin Ma , Yongliang Shen , Gongfan Fang , Chen Chen , Chenghao Jia , Weiming Lu

The knowledge distillation uses a high-performance teacher network to guide the student network. However, the performance gap between the teacher and student networks can affect the student's training. This paper proposes a novel knowledge…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Songling Zhu , Ronghua Shang , Bo Yuan , Weitong Zhang , Yangyang Li , Licheng Jiao

Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all existing KD algorithms are data-driven, i.e., relying on a large…

Machine Learning · Computer Science 2020-03-03 Gongfan Fang , Jie Song , Chengchao Shen , Xinchao Wang , Da Chen , Mingli Song

Deep pre-training and fine-tuning models (such as BERT and OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow.…

Computation and Language · Computer Science 2019-10-21 Ze Yang , Linjun Shou , Ming Gong , Wutao Lin , Daxin Jiang

Efficiently and reliably estimating uncertainty is an important objective in deep learning. It is especially pertinent to autoregressive sequence tasks, where training and inference costs are typically very high. However, existing research…

Machine Learning · Computer Science 2023-05-18 Yassir Fathullah , Guoxuan Xia , Mark Gales

Although more layers and more parameters generally improve the accuracy of the models, such big models generally have high computational complexity and require big memory, which exceed the capacity of small devices for inference and incurs…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-07-15 Ji Liu , Daxiang Dong , Xi Wang , An Qin , Xingjian Li , Patrick Valduriez , Dejing Dou , Dianhai Yu

Traditional knowledge distillation transfers "dark knowledge" of a pre-trained teacher network to a student network, and ignores the knowledge in the training process of the teacher, which we call teacher's experience. However, in realistic…

Computer Vision and Pattern Recognition · Computer Science 2022-02-28 Chaofei Wang , Shaowei Zhang , Shiji Song , Gao Huang

Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained…

Computation and Language · Computer Science 2023-02-21 Chen Liang , Haoming Jiang , Zheng Li , Xianfeng Tang , Bin Yin , Tuo Zhao

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Computation and Language · Computer Science 2024-06-18 Qihuang Zhong , Liang Ding , Li Shen , Juhua Liu , Bo Du , Dacheng Tao

This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNN-T) models. In hard distillation, a teacher model transcribes large amounts of unlabelled speech to train a student…

Computation and Language · Computer Science 2023-03-13 Mohammad Zeineldeen , Kartik Audhkhasi , Murali Karthick Baskar , Bhuvana Ramabhadran

Traditional knowledge distillation (KD) relies on a proficient teacher trained on the target task, which is not always available. In this setting, cross-task distillation can be used, enabling the use of any teacher model trained on a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Dylan Auty , Roy Miles , Benedikt Kolbeinsson , Krystian Mikolajczyk

Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…

Computation and Language · Computer Science 2020-01-17 Gustavo Aguilar , Yuan Ling , Yu Zhang , Benjamin Yao , Xing Fan , Chenlei Guo

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-20 Ji Won Yoon , Hyeonseung Lee , Hyung Yong Kim , Won Ik Cho , Nam Soo Kim

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…

Computation and Language · Computer Science 2023-11-27 Nathan Brown , Ashton Williamson , Tahj Anderson , Logan Lawrence

Knowledge distillation (KD) is a widely adopted approach for compressing large neural networks by transferring knowledge from a large teacher model to a smaller student model. In the context of large language models, token level KD,…

Computation and Language · Computer Science 2025-09-19 Yihan Cao , Yanbin Kang , Zhengming Xing , Ruijie Jiang

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is…

Machine Learning · Computer Science 2021-03-02 Jiaxi Tang , Rakesh Shivanna , Zhe Zhao , Dong Lin , Anima Singh , Ed H. Chi , Sagar Jain

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

Causal language models have demonstrated remarkable capabilities, but their size poses significant challenges for deployment in resource-constrained environments. Knowledge distillation, a widely-used technique for transferring knowledge…

Machine Learning · Computer Science 2025-03-03 Makoto Shing , Kou Misaki , Han Bao , Sho Yokoi , Takuya Akiba