English
Related papers

Related papers: Distilling Knowledge from Pre-trained Language Mod…

200 papers

In most natural language inference problems, sentence representation is needed for semantic retrieval tasks. In recent years, pre-trained large language models have been quite effective for computing such representations. These models…

Computation and Language · Computer Science 2023-04-26 Domagoj Ševerdija , Tomislav Prusina , Antonio Jovanović , Luka Borozan , Jurica Maltar , Domagoj Matijević

An increasing number of datasets sharing similar domains for semantic segmentation have been published over the past few years. But despite the growing amount of overall data, it is still difficult to train bigger and better models due to…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Anton Backhaus , Thorsten Luettel , Mirko Maehlisch

This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). Contemporary findings addressing this thesis statement take dichotomous standpoints: Muller et al. (2019) and Shen et al. (2021b).…

Machine Learning · Computer Science 2022-06-30 Keshigeyan Chandrasegaran , Ngoc-Trung Tran , Yunqing Zhao , Ngai-Man Cheung

In this paper, we show that knowledge distillation can be subverted to manipulate language model benchmark scores, revealing a critical vulnerability in current evaluation practices. We introduce "Data Laundering," a process that enables…

Computation and Language · Computer Science 2025-06-05 Jonibek Mansurov , Akhmed Sakip , Alham Fikri Aji

Modern Natural Language Generation (NLG) models come with massive computational and storage requirements. In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users. We…

Computation and Language · Computer Science 2023-05-29 Nitay Calderon , Subhabrata Mukherjee , Roi Reichart , Amir Kantor

Knowledge distillation (KD) aims to distill the knowledge from the teacher (larger) to the student (smaller) model via soft-label for the efficient neural network. In general, the performance of a model is determined by accuracy, which is…

Signal Processing · Electrical Eng. & Systems 2025-08-25 Stephen Ekaputra Limantoro

Knowledge distillation in machine learning is the process of transferring knowledge from a large model called the teacher to a smaller model called the student. Knowledge distillation is one of the techniques to compress the large network…

Machine Learning · Computer Science 2022-06-27 Durga Prasad Ganta , Himel Das Gupta , Victor S. Sheng

Neural approaches to ranking based on pre-trained language models are highly effective in ad-hoc search. However, the computational expense of these models can limit their application. As such, a process known as knowledge distillation is…

Information Retrieval · Computer Science 2024-11-05 Vishakha Suresh Kalal , Andrew Parry , Sean MacAvaney

We perform knowledge distillation (KD) benchmark from task-specific BERT-base teacher models to various student models: BiLSTM, CNN, BERT-Tiny, BERT-Mini, and BERT-Small. Our experiment involves 12 datasets grouped in two tasks: text…

Computation and Language · Computer Science 2022-01-04 Made Nindyatama Nityasya , Haryo Akbarianto Wibowo , Rendi Chevi , Radityo Eko Prasojo , Alham Fikri Aji

Knowledge distillation (KD) has proved to be an effective approach for deep neural network compression, which learns a compact network (student) by transferring the knowledge from a pre-trained, over-parameterized network (teacher). In…

Machine Learning · Computer Science 2021-04-13 Zi Wang

Optimizing neural networks with noisy labels is a challenging task, especially if the label set contains real-world noise. Networks tend to generalize to reasonable patterns in the early training stages and overfit to specific details of…

Computer Vision and Pattern Recognition · Computer Science 2023-04-27 Timo Kaiser , Lukas Ehmann , Christoph Reinders , Bodo Rosenhahn

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

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Guodong Xu , Ziwei Liu , Xiaoxiao Li , Chen Change Loy

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Artificial Intelligence · Computer Science 2023-01-31 Chaochen Gao , Xing Wu , Peng Wang , Jue Wang , Liangjun Zang , Zhongyuan Wang , Songlin Hu

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

Sound · Computer Science 2023-09-18 Rayan Daod Nathoo , Mikolaj Kegler , Marko Stamenovic

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to…

Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of enhancing teacher…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xin Zhang , Jianyang Xu , Hao Peng , Dongjing Wang , Jingyuan Zheng , Yu Li , Yuyu Yin , Hongbo Wang

Distilling knowledge from a large teacher model to a lightweight one is a widely successful approach for generating compact, powerful models in the semi-supervised learning setting where a limited amount of labeled data is available. In…

Machine Learning · Computer Science 2023-02-07 Cenk Baykal , Khoa Trinh , Fotis Iliopoulos , Gaurav Menghani , Erik Vee

Much research effort is being applied to the task of compressing the knowledge of self-supervised models, which are powerful, yet large and memory consuming. In this work, we show that the original method of knowledge distillation (and its…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Danilo de Oliveira , Timo Gerkmann

With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…

Computation and Language · Computer Science 2023-08-10 Shivam Sahni , Harsh Patel

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…

Machine Learning · Computer Science 2022-10-26 Dongkyu Lee , Ka Chun Cheung , Nevin L. Zhang