English
Related papers

Related papers: Structural Sensitivity in Compressed Transformers:…

200 papers

Transformer-based language models are applied to a wide range of applications in natural language processing. However, they are inefficient and difficult to deploy. In recent years, many compression algorithms have been proposed to increase…

Computation and Language · Computer Science 2021-11-11 Ofir Zafrir , Ariel Larey , Guy Boudoukh , Haihao Shen , Moshe Wasserblat

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…

Machine Learning · Computer Science 2024-04-10 Georgy Tyukin

Pre-trained universal feature extractors, such as BERT for natural language processing and VGG for computer vision, have become effective methods for improving deep learning models without requiring more labeled data. While effective,…

Computation and Language · Computer Science 2020-05-18 Mitchell A. Gordon , Kevin Duh , Nicholas Andrews

Contemporary state-of-the-art neural networks have increasingly large numbers of parameters, which prevents their deployment on devices with limited computational power. Pruning is one technique to remove unnecessary weights and reduce…

Machine Learning · Computer Science 2023-08-15 Sahel Mohammad Iqbal , Subhankar Mishra

This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less…

Computation and Language · Computer Science 2025-01-28 Xiaodong Chen , Yuxuan Hu , Jing Zhang , Yanling Wang , Cuiping Li , Hong Chen

Convolutional neural networks show outstanding results in a variety of computer vision tasks. However, a neural network architecture design usually faces a trade-off between model performance and computational/memory complexity. For some…

Computer Vision and Pattern Recognition · Computer Science 2020-06-12 Pavel Kaloshin

Network pruning and knowledge distillation are two widely-known model compression methods that efficiently reduce computation cost and model size. A common problem in both pruning and distillation is to determine compressed architecture,…

Computer Vision and Pattern Recognition · Computer Science 2022-02-23 Dongqi Wang , Shengyu Zhang , Zhipeng Di , Xin Lin , Weihua Zhou , Fei Wu

The rapid advancement of large-language models (LLMs) has driven extensive research into parameter compression after training has been completed, yet compression during the training phase remains largely unexplored. In this work, we…

Machine Learning · Computer Science 2025-11-19 Jun Wu , Jiangtao Wen , Yuxing Han

Resource-efficient convolution neural networks enable not only the intelligence on edge devices but also opportunities in system-level optimization such as scheduling. In this work, we aim to improve the performance of resource-constrained…

Computer Vision and Pattern Recognition · Computer Science 2018-10-19 Ting-Wu Chin , Cha Zhang , Diana Marculescu

Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for deployment on resource-constrained platforms. While model compression techniques such…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Abhinav Shukla , Nachiket Tapas

Pruning convolutional filters has demonstrated its effectiveness in compressing ConvNets. Prior art in filter pruning requires users to specify a target model complexity (e.g., model size or FLOP count) for the resulting architecture.…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Ting-Wu Chin , Ruizhou Ding , Cha Zhang , Diana Marculescu

Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion, which brings considerable costs to both model training and inference. However, existing methods such as model quantization, knowledge…

Computation and Language · Computer Science 2024-10-16 Yifei Yang , Zouying Cao , Hai Zhao

Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the…

Machine Learning · Computer Science 2017-06-06 Huizi Mao , Song Han , Jeff Pool , Wenshuo Li , Xingyu Liu , Yu Wang , William J. Dally

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Computation and Language · Computer Science 2022-01-19 Dongkuan Xu , Ian E. H. Yen , Jinxi Zhao , Zhibin Xiao

This paper proposes \textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers. Layer fusion can significantly reduce…

Machine Learning · Computer Science 2020-07-30 James O' Neill , Greg Ver Steeg , Aram Galstyan

Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation…

Computation and Language · Computer Science 2023-03-01 Yifan Peng , Kwangyoun Kim , Felix Wu , Prashant Sridhar , Shinji Watanabe

Speech representation models based on the transformer architecture and trained by self-supervised learning have shown great promise for solving tasks such as speech and speaker recognition, keyword spotting, emotion detection, and more.…

Computation and Language · Computer Science 2024-11-25 Teresa Dorszewski , Lenka Tětková , Lars Kai Hansen

Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks…

Machine Learning · Statistics 2017-11-15 Michael Zhu , Suyog Gupta

Large Language Models excel at natural language processing tasks, but their massive size leads to high computational and storage demands. Recent works have sought to reduce their model size through layer-wise structured pruning. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Fei Wang , Li Shen , Liang Ding , Chao Xue , Ye Liu , Changxing Ding

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Computation and Language · Computer Science 2026-04-17 Andrew Kiruluta