English
Related papers

Related papers: ReplaceMe: Network Simplification via Depth Prunin…

200 papers

We propose a new gradient-based approach for extracting sub-architectures from a given large model. Contrarily to existing pruning methods, which are unable to disentangle the network architecture and the corresponding weights, our…

Machine Learning · Computer Science 2021-07-08 Nicolo Colombo , Yang Gao

Structured pruning is a promising hardware-friendly compression technique for large language models (LLMs), which is expected to be retraining-free to avoid the enormous retraining cost. This retraining-free paradigm involves (1) pruning…

Machine Learning · Computer Science 2024-07-19 Pingjie Wang , Ziqing Fan , Shengchao Hu , Zhe Chen , Yanfeng Wang , Yu Wang

This paper describes a channel-selection approach for simplifying deep neural networks. Specifically, we propose a new type of generic network layer, called pruning layer, to seamlessly augment a given pre-trained model for compression.…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Chih-Yao Chiu , Hwann-Tzong Chen , Tyng-Luh Liu

N:M structured pruning is essential for large language models (LLMs) because it can remove less important network weights and reduce the memory and computation requirements. Existing pruning methods mainly focus on designing metrics to…

Computation and Language · Computer Science 2025-03-17 Chi Xu , Gefei Zhang , Yantong Zhu , Luca Benini , Guosheng Hu , Yawei Li , Zhihong Zhang

Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compute a necessity, while raising environmental concerns. To…

Machine Learning · Computer Science 2024-10-22 Yang Zhang , Yawei Li , Xinpeng Wang , Qianli Shen , Barbara Plank , Bernd Bischl , Mina Rezaei , Kenji Kawaguchi

Weight pruning methods for deep neural networks (DNNs) have been investigated recently, but prior work in this area is mainly heuristic, iterative pruning, thereby lacking guarantees on the weight reduction ratio and convergence time. To…

Neural and Evolutionary Computing · Computer Science 2018-10-23 Tianyun Zhang , Shaokai Ye , Kaiqi Zhang , Jian Tang , Wujie Wen , Makan Fardad , Yanzhi Wang

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically…

Machine Learning · Computer Science 2021-03-11 Lorenz Kuhn , Clare Lyle , Aidan N. Gomez , Jonas Rothfuss , Yarin Gal

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained…

As we push the boundaries of performance in various vision tasks, the models grow in size correspondingly. To keep up with this growth, we need very aggressive pruning techniques for efficient inference and deployment on edge devices.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-19 Xinglong Sun , Barath Lakshmanan , Maying Shen , Shiyi Lan , Jingde Chen , Jose Alvarez

Deep Neural Networks (DNNs) are often over-parameterized for their tasks and can be compressed quite drastically by removing weights, a process called pruning. We investigate the impact of different pruning techniques on the classification…

Machine Learning · Computer Science 2026-05-26 Jonathan von Rad , Florian Seuffert

Synaptic pruning in biological brains removes weak connections to improve efficiency. In contrast, dropout regularization in artificial neural networks randomly deactivates neurons without considering activity-dependent pruning. We propose…

Machine Learning · Computer Science 2025-10-07 Gideon Vos , Liza van Eijk , Zoltan Sarnyai , Mostafa Rahimi Azghadi

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

With the rapid expansion of large language models (LLMs), the demand for memory and computational resources has grown significantly. Recent advances in LLM pruning aim to reduce the size and computational cost of these models. However,…

Machine Learning · Computer Science 2025-05-29 Zhendong Mi , Zhenglun Kong , Geng Yuan , Shaoyi Huang

Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of the traditional…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Jiaqi Li , Haoran Li , Yaran Chen , Zixiang Ding , Nannan Li , Mingjun Ma , Zicheng Duan , Dongbing Zhao

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

Many applications, especially in physics and other sciences, call for easily interpretable and robust machine learning techniques. We propose a fully gradient-based technique for training radial basis function networks with an efficient and…

Machine Learning · Computer Science 2022-09-30 Jussi Määttä , Viacheslav Bazaliy , Jyri Kimari , Flyura Djurabekova , Kai Nordlund , Teemu Roos

Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token efficiency compared to training…

Computation and Language · Computer Science 2025-03-11 Yixiao Li , Xianzhi Du , Ajay Jaiswal , Tao Lei , Tuo Zhao , Chong Wang , Jianyu Wang

We propose an efficient and unified framework, namely ThiNet, to simultaneously accelerate and compress CNN models in both training and inference stages. We focus on the filter level pruning, i.e., the whole filter would be discarded if it…

Computer Vision and Pattern Recognition · Computer Science 2017-07-21 Jian-Hao Luo , Jianxin Wu , Weiyao Lin

Modern deep neural networks require a significant amount of computing time and power to train and deploy, which limits their usage on edge devices. Inspired by the iterative weight pruning in the Lottery Ticket Hypothesis, we propose…

Machine Learning · Computer Science 2022-07-15 John Tan Chong Min , Mehul Motani

Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning parameters, however, exhibit vastly different parallelism…

Machine Learning · Computer Science 2019-05-15 Dongsoo Lee , Se Jung Kwon , Byeongwook Kim , Parichay Kapoor , Gu-Yeon Wei