English
Related papers

Related papers: Neural Passage Quality Estimation for Static Pruni…

200 papers

The remarkable performance of modern deep neural networks (DNNs) is largely driven by their massive scale, often comprising tens to hundreds of millions-or even billions-of parameters. However, such a scale incurs substantial storage and…

Machine Learning · Computer Science 2026-05-01 Mingyuan Wang , Yangzi Guo , Sida Liu , Yuhang Liu

Large volumes of text data have contributed significantly to the development of large language models (LLMs) in recent years. This data is typically acquired by scraping the internet, leading to pretraining datasets comprised of noisy web…

Computation and Language · Computer Science 2023-09-12 Max Marion , Ahmet Üstün , Luiza Pozzobon , Alex Wang , Marzieh Fadaee , Sara Hooker

The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one or more of the…

Machine Learning · Computer Science 2020-10-13 Sai Aparna Aketi , Sourjya Roy , Anand Raghunathan , Kaushik Roy

Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work typically treats layer redundancy as an inherent structural property of pretrained networks, emphasizing importance criteria…

Machine Learning · Computer Science 2026-05-28 Minkyu Kim , Vincent-Daniel Yun , Youngrae Kim , Suin Cho , Woosang Lim , Sunwoo Lee

Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value. The current work focuses on fine-grained pruning, which uses…

Machine Learning · Computer Science 2022-09-28 Xiatao Kang , Ping Li , Jiayi Yao , Chengxi Li

In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN). The objective is to heavily prune convolutional edges while maintaining retrieval…

Computer Vision and Pattern Recognition · Computer Science 2017-07-19 Gaurav Manek , Jie Lin , Vijay Chandrasekhar , Lingyu Duan , Sateesh Giduthuri , Xiaoli Li , Tomaso Poggio

Traditional information retrieval (IR) ranking models process the full text of documents. Newer models based on Transformers, however, would incur a high computational cost when processing long texts, so typically use only snippets from the…

Information Retrieval · Computer Science 2022-01-24 Gabriella Kazai , Bhaskar Mitra , Anlei Dong , Nick Craswell , Linjun Yang

The leap in performance in state-of-the-art computer vision methods is attributed to the development of deep neural networks. However it often comes at a computational price which may hinder their deployment. To alleviate this limitation,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Edouard Yvinec , Arnaud Dapogny , Matthieu Cord , Kevin Bailly

Given the vast scale of the Web, crawling prioritisation techniques based on link graph traversal, popularity, link analysis, and textual content are frequently applied to surface documents that are most likely to be valuable. While…

Information Retrieval · Computer Science 2025-07-03 Francesca Pezzuti , Sean MacAvaney , Nicola Tonellotto

Channel-based pruning has achieved significant successes in accelerating deep convolutional neural network, whose pipeline is an iterative three-step procedure: ranking, pruning and fine-tuning. However, this iterative procedure is…

Computer Vision and Pattern Recognition · Computer Science 2019-02-19 Zi Wang , Chengcheng Li , Dali Wang , Xiangyang Wang , Hairong Qi

Dataset pruning is the process of removing sub-optimal tuples from a dataset to improve the learning of a machine learning model. In this paper, we compared the performance of different algorithms, first on an unpruned dataset and then on…

Machine Learning · Computer Science 2019-01-31 Arun Thundyill Saseendran , Lovish Setia , Viren Chhabria , Debrup Chakraborty , Aneek Barman Roy

We propose three novel pruning techniques to improve the cost and results of inference-aware Differentiable Neural Architecture Search (DNAS). First, we introduce Prunode, a stochastic bi-path building block for DNAS, which can search over…

Machine Learning · Computer Science 2023-01-06 Sławomir Kierat , Mateusz Sieniawski , Denys Fridman , Chen-Han Yu , Szymon Migacz , Paweł Morkisz , Alex-Fit Florea

Foundation models and their checkpoints have significantly advanced deep learning, boosting performance across various applications. However, fine-tuned models often struggle outside their specific domains and exhibit considerable…

Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent structures in many…

Machine Learning · Statistics 2024-03-25 Takashi Furuya , Kazuma Suetake , Koichi Taniguchi , Hiroyuki Kusumoto , Ryuji Saiin , Tomohiro Daimon

Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models…

Computation and Language · Computer Science 2017-05-02 Adams Wei Yu , Hongrae Lee , Quoc V. Le

The recent MSMARCO passage retrieval collection has allowed researchers to develop highly tuned retrieval systems. One aspect of this data set that makes it distinctive compared to traditional corpora is that most of the topics only have a…

Information Retrieval · Computer Science 2022-01-12 Joel Mackenzie , Matthias Petri , Alistair Moffat

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks…

Machine Learning · Computer Science 2020-01-15 Kimessha Paupamah , Steven James , Richard Klein

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

Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Such models, however, are restricted by a high computational overhead, limiting their applicability and hindering advancements in the…

Machine Learning · Computer Science 2024-11-05 Ian Pons , Bruno Yamamoto , Anna H. Reali Costa , Artur Jordao

Neural network pruning is frequently used to compress over-parameterized networks by large amounts, while incurring only marginal drops in generalization performance. However, the impact of pruning on networks that have been highly…

Computer Vision and Pattern Recognition · Computer Science 2023-01-12 Sayan Ghosh , Karthik Prasad , Xiaoliang Dai , Peizhao Zhang , Bichen Wu , Graham Cormode , Peter Vajda