English
Related papers

Related papers: Distilling HuBERT with LSTMs via Decoupled Knowled…

200 papers

Even though deep speaker models have demonstrated impressive accuracy in speaker verification tasks, this often comes at the expense of increased model size and computation time, presenting challenges for deployment in resource-constrained…

Sound · Computer Science 2023-12-21 Xuechen Liu , Md Sahidullah , Tomi Kinnunen

Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the…

Machine Learning · Computer Science 2020-04-01 Tianhong Li , Jianguo Li , Zhuang Liu , Changshui Zhang

Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…

Machine Learning · Computer Science 2025-09-25 Feiyang Fu , Tongxian Guo , Zhaoqiang Liu

Albeit great performance of Transformer-based speech selfsupervised learning (SSL) models, their large parameter size and computational cost make them unfavorable to utilize. In this study, we propose to compress the speech SSL models by…

Sound · Computer Science 2024-04-26 Kangwook Jang , Sungnyun Kim , Hoirin Kim

Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our…

Computation and Language · Computer Science 2020-10-07 Alexander Hoyle , Pranav Goel , Philip Resnik

How to learn highly compact yet effective sentence representation? Pre-trained language models have been effective in many NLP tasks. However, these models are often huge and produce large sentence embeddings. Moreover, there is a big…

Computation and Language · Computer Science 2022-03-16 Xuandong Zhao , Zhiguo Yu , Ming Wu , Lei Li

Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Shengcao Cao , Mengtian Li , James Hays , Deva Ramanan , Yi-Xiong Wang , Liang-Yan Gui

Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Kai Wang , Fei Yang , Joost van de Weijer

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents…

Computation and Language · Computer Science 2022-12-08 Haihao Shen , Ofir Zafrir , Bo Dong , Hengyu Meng , Xinyu Ye , Zhe Wang , Yi Ding , Hanwen Chang , Guy Boudoukh , Moshe Wasserblat

Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another. In particular, when the architectures are identical, this is called self-distillation. The idea is to feed in…

Machine Learning · Computer Science 2020-10-27 Hossein Mobahi , Mehrdad Farajtabar , Peter L. Bartlett

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

We generalize deep self-attention distillation in MiniLM (Wang et al., 2020) by only using self-attention relation distillation for task-agnostic compression of pretrained Transformers. In particular, we define multi-head self-attention…

Computation and Language · Computer Science 2021-06-29 Wenhui Wang , Hangbo Bao , Shaohan Huang , Li Dong , Furu Wei

Compressing deep networks is essential to expand their range of applications to constrained settings. The need for compression however often arises long after the model was trained, when the original data might no longer be available. On…

Machine Learning · Computer Science 2022-01-19 Jean-Michel Begon , Pierre Geurts

The rapid advancement of large language models (LLMs) has significantly advanced the capabilities of artificial intelligence across various domains. However, their massive scale and high computational costs render them unsuitable for direct…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Miao Rang , Zhenni Bi , Hang Zhou , Hanting Chen , An Xiao , Tianyu Guo , Kai Han , Xinghao Chen , Yunhe Wang

Deep learning networks have achieved state-of-the-art accuracies on computer vision workloads like image classification and object detection. The performant systems, however, typically involve big models with numerous parameters. Once…

Machine Learning · Computer Science 2017-11-17 Asit Mishra , Debbie Marr

Transformer-based detectors (DETRs) are becoming popular for their simple framework, but the large model size and heavy time consumption hinder their deployment in the real world. While knowledge distillation (KD) can be an appealing…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Jiahao Chang , Shuo Wang , Haiming Xu , Zehui Chen , Chenhongyi Yang , Feng Zhao

What does a neural network learn when training from a task-specific dataset? Synthesizing this knowledge is the central idea behind Dataset Distillation, which recent work has shown can be used to compress large datasets into a small set of…

Machine Learning · Computer Science 2024-03-05 Tian Qin , Zhiwei Deng , David Alvarez-Melis

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 is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Roy Miles , Ismail Elezi , Jiankang Deng

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
‹ Prev 1 8 9 10 Next ›