English
Related papers

Related papers: Sequence-Level Knowledge Distillation

200 papers

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic…

Computer Vision and Pattern Recognition · Computer Science 2019-10-31 Tao Wang , Li Yuan , Xiaopeng Zhang , Jiashi Feng

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…

Computation and Language · Computer Science 2020-04-07 Wenhui Wang , Furu Wei , Li Dong , Hangbo Bao , Nan Yang , Ming Zhou

We propose utilizing n-best reranking to enhance Sequence-Level Knowledge Distillation (Kim and Rush, 2016) where we extract pseudo-labels for student model's training data from top n-best hypotheses and leverage a diverse set of models…

Computation and Language · Computer Science 2024-06-14 Hendra Setiawan

Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although great success has been achieved by prior distillation methods…

Machine Learning · Computer Science 2021-08-31 Yuzhang Shang , Bin Duan , Ziliang Zong , Liqiang Nie , Yan Yan

This paper presents a method to interpret the success of knowledge distillation by quantifying and analyzing task-relevant and task-irrelevant visual concepts that are encoded in intermediate layers of a deep neural network (DNN). More…

Machine Learning · Computer Science 2020-03-26 Xu Cheng , Zhefan Rao , Yilan Chen , Quanshi Zhang

The carbon footprint of natural language processing research has been increasing in recent years due to its reliance on large and inefficient neural network implementations. Distillation is a network compression technique which attempts to…

Computation and Language · Computer Science 2020-06-02 Mark Anderson , Carlos Gómez-Rodríguez

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

Large language models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing (NLP) tasks. However, these models are often difficult to deploy due to significant computational requirements and…

Computation and Language · Computer Science 2024-12-25 Vijay Goyal , Mustafa Khan , Aprameya Tirupati , Harveer Saini , Michael Lam , Kevin Zhu

Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Zhiyuan Fang , Jianfeng Wang , Xiaowei Hu , Lijuan Wang , Yezhou Yang , Zicheng Liu

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 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

Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 Frederick Tung , Greg Mori

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

Computation and Language · Computer Science 2025-07-22 Xiandong Meng , Yan Wu , Yexin Tian , Xin Hu , Tianze Kang , Junliang Du

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

Computation and Language · Computer Science 2025-08-05 Suhas Kamasetty Ramesh , Ayan Sengupta , Tanmoy Chakraborty

The advent of large pre-trained language models has given rise to rapid progress in the field of Natural Language Processing (NLP). While the performance of these models on standard benchmarks has scaled with size, compression techniques…

Computation and Language · Computer Science 2021-05-14 Ahmad Rashid , Vasileios Lioutas , Mehdi Rezagholizadeh

Deep pre-training and fine-tuning models (like BERT, 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. How to…

Computation and Language · Computer Science 2019-04-23 Ze Yang , Linjun Shou , Ming Gong , Wutao Lin , Daxin Jiang

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

Standard neural machine translation (NMT) is on the assumption of document-level context independent. Most existing document-level NMT methods are satisfied with a smattering sense of brief document-level information, while this work…

Computation and Language · Computer Science 2021-10-13 Shu Jiang , Hai Zhao , Zuchao Li , Bao-Liang Lu

Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance. Previous studies have shown that DWT can be effective in the vision domain…

Computation and Language · Computer Science 2023-05-30 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Sung Ju Hwang , Alexander Min

Knowledge distillation typically involves transferring knowledge from a Large Language Model (LLM) to a Smaller Language Model (SLM). However, in tasks such as text matching, fine-tuned smaller models often yield more effective…

Computation and Language · Computer Science 2025-07-09 Mingzhe Li , Jing Xiang , Qishen Zhang , Kaiyang Wan , Xiuying Chen