English
Related papers

Related papers: STAT: Shrinking Transformers After Training

200 papers

Structured pruning efficiently compresses networks by identifying and removing unimportant neurons. While this can be elegantly achieved by applying sparsity-inducing regularisation on BatchNorm parameters, an L1 penalty would shrink all…

Machine Learning · Computer Science 2022-04-14 Mihai Suteu , Yike Guo

Model compression by way of parameter pruning, quantization, or distillation has recently gained popularity as an approach for reducing the computational requirements of modern deep neural network models for NLP. Inspired by prior works…

Computation and Language · Computer Science 2023-10-10 Clara Na , Sanket Vaibhav Mehta , Emma Strubell

We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning…

Machine Learning · Computer Science 2023-03-23 Elias Frantar , Dan Alistarh

Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural…

Machine Learning · Computer Science 2019-07-02 Jonathan Frankle , David Bau

We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional…

Computation and Language · Computer Science 2026-02-20 Dmitriy Shopkhoev , Ammar Ali , Magauiya Zhussip , Valentin Malykh , Stamatios Lefkimmiatis , Nikos Komodakis , Sergey Zagoruyko

Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…

Computation and Language · Computer Science 2023-05-31 Arash Ardakani , Altan Haan , Shangyin Tan , Doru Thom Popovici , Alvin Cheung , Costin Iancu , Koushik Sen

Deep spiking neural networks (SNNs) have emerged as a potential alternative to traditional deep learning frameworks, due to their promise to provide increased compute efficiency on event-driven neuromorphic hardware. However, to perform…

Neural and Evolutionary Computing · Computer Science 2021-07-28 Souvik Kundu , Gourav Datta , Massoud Pedram , Peter A. Beerel

Network pruning has been the driving force for the acceleration of neural networks and the alleviation of model storage/transmission burden. With the advent of AutoML and neural architecture search (NAS), pruning has become topical with…

Computer Vision and Pattern Recognition · Computer Science 2020-08-04 Yawei Li , Shuhang Gu , Kai Zhang , Luc Van Gool , Radu Timofte

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

In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Zechun Liu , Haoyuan Mu , Xiangyu Zhang , Zichao Guo , Xin Yang , Tim Kwang-Ting Cheng , Jian Sun

Convolutional Neural Networks (CNNs) have achieved significant breakthroughs in various fields. However, these advancements have led to a substantial increase in the complexity and size of these networks. This poses a challenge when…

Machine Learning · Computer Science 2025-09-11 Ahmed Sadaqa , Di Liu

DNN pruning is a popular way to reduce the size of a model, improve the inference latency, and minimize the power consumption on DNN accelerators. However, existing approaches might be too complex, expensive or ineffective to apply to a…

Machine Learning · Computer Science 2023-11-21 Minsik Cho , Saurabh Adya , Devang Naik

Overparameterization has been shown to benefit both the optimization and generalization of neural networks, but large networks are resource hungry at both training and test time. Network pruning can reduce test-time resource requirements,…

Machine Learning · Computer Science 2020-08-10 Chaoqi Wang , Guodong Zhang , Roger Grosse

Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them…

Computer Vision and Pattern Recognition · Computer Science 2021-02-08 Gedeon Muhawenayo , Georgia Gkioxari

Model compression techniques, such as pruning and quantization, are becoming increasingly important to reduce the memory footprints and the amount of computations. Despite model size reduction, achieving performance enhancement on devices…

Machine Learning · Computer Science 2020-03-06 Se Jung Kwon , Dongsoo Lee , Byeongwook Kim , Parichay Kapoor , Baeseong Park , Gu-Yeon Wei

We introduce EELBERT, an approach for compression of transformer-based models (e.g., BERT), with minimal impact on the accuracy of downstream tasks. This is achieved by replacing the input embedding layer of the model with dynamic, i.e.…

Computation and Language · Computer Science 2023-11-01 Gabrielle Cohn , Rishika Agarwal , Deepanshu Gupta , Siddharth Patwardhan

To remove redundant components of large language models (LLMs) without incurring significant computational costs, this work focuses on single-shot pruning without a retraining phase. We simplify the pruning process for Transformer-based…

Artificial Intelligence · Computer Science 2024-07-30 Jianwei Li , Yijun Dong , Qi Lei

Pre-trained large-scale language models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. However, the limited weight storage and computational speed on hardware platforms have impeded the…

Computation and Language · Computer Science 2020-11-18 Bingbing Li , Zhenglun Kong , Tianyun Zhang , Ji Li , Zhengang Li , Hang Liu , Caiwen Ding

Pre-trained language models achieve superior performance but are computationally expensive. Techniques such as pruning and knowledge distillation have been developed to reduce their sizes and latencies. In this work, we propose a structured…

Computation and Language · Computer Science 2023-05-19 Ziqing Yang , Yiming Cui , Xin Yao , Shijin Wang

In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Baiyu Pan , Jichao Jiao , Jianxing Pang , Jun Cheng
‹ Prev 1 3 4 5 6 7 10 Next ›