English
Related papers

Related papers: GAPrune: Gradient-Alignment Pruning for Domain-Awa…

200 papers

For many applications, utilizing DNNs (Deep Neural Networks) requires their implementation on a target architecture in an optimized manner concerning energy consumption, memory requirement, throughput, etc. DNN compression is used to reduce…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Muhammad Sabih , Frank Hannig , Juergen Teich

In Machine Learning, Artificial Neural Networks (ANNs) are a very powerful tool, broadly used in many applications. Often, the selected (deep) architectures include many layers, and therefore a large amount of parameters, which makes…

Machine Learning · Computer Science 2022-06-29 Matteo Cacciola , Antonio Frangioni , Xinlin Li , Andrea Lodi

Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies reveal significant redundancy in LLMs layers, making layer pruning an active research…

Computation and Language · Computer Science 2026-02-17 Hao Liu , Guangyan Li , Wensheng Zhang , Yongqiang Tang

As deep neural networks (DNNs) are increasingly deployed on edge devices, optimizing models for constrained computational resources is critical. Existing auto-pruning methods face challenges due to the diversity of DNN models, various…

Artificial Intelligence · Computer Science 2026-04-21 Lixian Jing , Jianpeng Qi , Junyu Dong , Yanwei Yu

This paper improves upon existing data pruning methods for image classification by introducing a novel pruning metric and pruning procedure based on importance sampling. The proposed pruning metric explicitly accounts for data separability,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Steven Grosz , Rui Zhao , Rajeev Ranjan , Hongcheng Wang , Manoj Aggarwal , Gerard Medioni , Anil Jain

Graph Neural Networks (GNNs) are proven to be powerful models to generate node embedding for downstream applications. However, due to the high computation complexity of GNN inference, it is hard to deploy GNNs for large-scale or real-time…

Machine Learning · Computer Science 2021-05-11 Hongkuan Zhou , Ajitesh Srivastava , Hanqing Zeng , Rajgopal Kannan , Viktor Prasanna

Pruning techniques are used comprehensively to compress convolutional neural networks (CNNs) on image classification. However, the majority of pruning methods require a well pre-trained model to provide useful supporting parameters, such as…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Yiheng Lu , Maoguo Gong , Wei Zhao , Kaiyuan Feng , Hao Li

The rapidly growing parameter volume of deep neural networks (DNNs) hinders the artificial intelligence applications on resource constrained devices, such as mobile and wearable devices. Neural network pruning, as one of the mainstream…

Machine Learning · Computer Science 2019-11-21 Ao Ren , Tao Zhang , Yuhao Wang , Sheng Lin , Peiyan Dong , Yen-kuang Chen , Yuan Xie , Yanzhi Wang

We introduce a pruning algorithm that provably sparsifies the parameters of a trained model in a way that approximately preserves the model's predictive accuracy. Our algorithm uses a small batch of input points to construct a data-informed…

Machine Learning · Computer Science 2021-03-16 Cenk Baykal , Lucas Liebenwein , Igor Gilitschenski , Dan Feldman , Daniela Rus

Deep learning model compression is an improving and important field for the edge deployment of deep learning models. Given the increasing size of the models and their corresponding power consumption, it is vital to decrease the model size…

Machine Learning · Computer Science 2022-10-12 Madhumitha Sakthi , Niranjan Yadla , Raj Pawate

Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both the general-domain and in-domain. However, the existing methods for domain adaptation usually suffer…

Computation and Language · Computer Science 2021-04-15 Shuhao Gu , Yang Feng , Wanying Xie

Deep neural networks (DNNs) have demonstrated remarkable performance in many tasks but it often comes at a high computational cost and memory usage. Compression techniques, such as pruning and quantization, are applied to reduce the memory…

Machine Learning · Computer Science 2025-07-09 Kimia Soroush , Mohsen Raji , Behnam Ghavami

In the arena of language model fine-tuning, the traditional approaches, such as Domain-Adaptive Pretraining (DAPT) and Task-Adaptive Pretraining (TAPT), although effective, but computational intensive. This research introduces a novel…

Computation and Language · Computer Science 2024-05-10 Keyu Chen , Yuan Pang , Zi Yang

State-of-the-art text-to-image diffusion models (DMs) achieve remarkable quality, yet their massive parameter scale (8-11B) poses significant challenges for inferences on resource-constrained devices. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Young D. Kwon , Rui Li , Sijia Li , Da Li , Sourav Bhattacharya , Stylianos I. Venieris

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources. To enable the deployment of modern models on resource-constrained…

Machine Learning · Computer Science 2024-08-12 Hongrong Cheng , Miao Zhang , Javen Qinfeng Shi

The adoption of Foundation Models in resource-constrained environments remains challenging due to their large size and inference costs. A promising way to overcome these limitations is post-training compression, which aims to balance…

Deep neural network pruning and quantization techniques have demonstrated it is possible to achieve high levels of compression with surprisingly little degradation to test set accuracy. However, this measure of performance conceals…

Machine Learning · Computer Science 2021-09-07 Sara Hooker , Aaron Courville , Gregory Clark , Yann Dauphin , Andrea Frome

Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not…

Machine Learning · Computer Science 2024-12-20 Lanxiang Hu , Tajana Rosing , Hao Zhang

Given a pretrained encoder-based language model, how can we accurately compress it without retraining? Retraining-free structured pruning algorithms are crucial in pretrained language model compression due to their significantly reduced…

Computation and Language · Computer Science 2024-03-18 Seungcheol Park , Hojun Choi , U Kang

Model pruning technique is vital for accelerating large language models by reducing their size and computational requirements. However, the generalizability of existing pruning methods across diverse datasets and tasks remains unclear.…

Computation and Language · Computer Science 2025-03-04 Yizhuo Ding , Xinwei Sun , Yanwei Fu , Guosheng Hu