English
Related papers

Related papers: Depth Pruning with Auxiliary Networks for TinyML

200 papers

Pruning provides a practical solution to reduce the resources required to run large language models (LLMs) to benefit from their effective capabilities as well as control their cost for training and inference. Research on LLM pruning often…

Computation and Language · Computer Science 2025-10-28 Yuanhe Tian , Junjie Liu , Xican Yang , Haishan Ye , Yan Song

Structured pruning reduces the computational overhead of deep neural networks by removing redundant sub-structures. However, assessing the relative importance of different sub-structures remains a significant challenge, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Gongfan Fang , Xinyin Ma , Michael Bi Mi , Xinchao Wang

Embedded and personal IoT devices are powered by microcontroller units (MCUs), whose extreme resource scarcity is a major obstacle for applications relying on on-device deep learning inference. Orders of magnitude less storage, memory and…

Machine Learning · Computer Science 2022-12-09 Edgar Liberis , Nicholas D. Lane

Network pruning is an effective method to reduce the computational expense of over-parameterized neural networks for deployment on low-resource systems. Recent state-of-the-art techniques for retraining pruned networks such as weight…

Machine Learning · Computer Science 2021-05-10 Duong H. Le , Binh-Son Hua

Convolutional neural networks are prevailing in deep learning tasks. However, they suffer from massive cost issues when working on mobile devices. Network pruning is an effective method of model compression to handle such problems. This…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Zhaofeng Si , Honggang Qi , Xiaoyu Song

Multi-modal Large Language Models (MLLMs) have achieved remarkable success by integrating visual and textual modalities. However, they incur significant computational overhead due to the large number of vision tokens processed, limiting…

Computation and Language · Computer Science 2025-03-11 Yizheng Sun , Yanze Xin , Hao Li , Jingyuan Sun , Chenghua Lin , Riza Batista-Navarro

How can we accelerate large language models(LLMs) without sacrificing accuracy? The slow inference speed of LLMs hinders us to benefit from their remarkable performance in diverse applications. This is mainly because numerous sublayers are…

Computation and Language · Computer Science 2025-06-05 Seungcheol Park , Sojin Lee , Jongjin Kim , Jinsik Lee , Hyunjik Jo , U Kang

Most neural network pruning methods, such as filter-level and layer-level prunings, prune the network model along one dimension (depth, width, or resolution) solely to meet a computational budget. However, such a pruning policy often leads…

Computer Vision and Pattern Recognition · Computer Science 2021-06-16 Wenxiao Wang , Minghao Chen , Shuai Zhao , Long Chen , Jinming Hu , Haifeng Liu , Deng Cai , Xiaofei He , Wei Liu

This paper presents an efficient and robust approach for reducing the size of deep neural networks by pruning entire neurons. It exploits maxout units for combining neurons into more complex convex functions and it makes use of a local…

Computer Vision and Pattern Recognition · Computer Science 2017-07-24 Fernando Moya Rueda , Rene Grzeszick , Gernot A. Fink

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary…

One of the major challenges in deploying deep neural network architectures is their size which has an adverse effect on their inference time and memory requirements. Deep CNNs can either be pruned width-wise by removing filters based on…

Computer Vision and Pattern Recognition · Computer Science 2020-10-07 Muhammad Umair Haider , Murtaza Taj

Deep learning approaches have provided state-of-the-art performance in many applications by relying on large and overparameterized neural networks. However, such networks have been shown to be very brittle and are difficult to deploy on…

Human-Computer Interaction · Computer Science 2023-10-26 Zhimin Li , Shusen Liu , Xin Yu , Kailkhura Bhavya , Jie Cao , Diffenderfer James Daniel , Peer-Timo Bremer , Valerio Pascucci

Neural networks grow vastly in size to tackle more sophisticated tasks. In many cases, such large networks are not deployable on particular hardware and need to be reduced in size. Pruning techniques help to shrink deep neural networks to…

Machine Learning · Computer Science 2022-06-01 Udo Schlegel , Samuel Schiegg , Daniel A. Keim

The bottleneck associated with the key-value(KV) cache presents a significant challenge during the inference processes of large language models. While depth pruning accelerates inference, it requires extensive recovery training, which can…

Computation and Language · Computer Science 2024-09-18 Bo Lv , Quan Zhou , Xuanang Ding , Yan Wang , Zeming Ma

Deep neural networks have been applied in many applications exhibiting extraordinary abilities in the field of computer vision. However, complex network architectures challenge efficient real-time deployment and require significant…

Computer Vision and Pattern Recognition · Computer Science 2021-06-16 Tailin Liang , John Glossner , Lei Wang , Shaobo Shi , Xiaotong Zhang

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

Making large language models (LLMs) more efficient in memory, latency, and serving cost is crucial for edge deployment, interactive applications, and sustainable inference at scale. Pruning is a promising technique, but existing pruning…

Computation and Language · Computer Science 2025-10-13 Eugene Kwek , Wenpeng Yin

Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumption. Two popular…

Machine Learning · Computer Science 2021-07-21 Benjamin Hawks , Javier Duarte , Nicholas J. Fraser , Alessandro Pappalardo , Nhan Tran , Yaman Umuroglu

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

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