English
Related papers

Related papers: NLU on Data Diets: Dynamic Data Subset Selection f…

200 papers

Recently, large language and vision models have shown strong performance, but due to high pre-training and fine-tuning costs, research has shifted towards faster training via dataset pruning. Previous methods used sample loss as an…

Machine Learning · Computer Science 2026-01-13 Jinying Xiao , Ping Li , Jie Nie , Bin Ji , Shasha Li , Xiaodong Liu , Jun Ma , Qingbo Wu , Jie Yu

Filter level pruning is an effective method to accelerate the inference speed of deep CNN models. Although numerous pruning algorithms have been proposed, there are still two open issues. The first problem is how to prune residual…

Computer Vision and Pattern Recognition · Computer Science 2020-04-28 Jian-Hao Luo , Jianxin Wu

Large language models (LLMs) achieve remarkable performance across tasks but incur substantial computational costs due to their deep, multi-layered architectures. Layer pruning has emerged as a strategy to alleviate these inefficiencies,…

Computation and Language · Computer Science 2025-06-05 Anhao Zhao , Fanghua Ye , Yingqi Fan , Junlong Tong , Zhiwei Fei , Hui Su , Xiaoyu Shen

Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This could mistakenly lead to preserving noisy samples due to their high loss values, resulting…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Huaiyuan Qin , Muli Yang , Gabriel James Goenawan , Kai Wang , Zheng Wang , Peng Hu , Xi Peng , Hongyuan Zhu

We propose a novel method for training a neural network for image classification to reduce input data dynamically, in order to reduce the costs of training a neural network model. As Deep Learning tasks become more popular, their…

Machine Learning · Computer Science 2025-10-10 Dominic Sanderson , Tatiana Kalgonova

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

Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale poses significant challenges for practical deployment. Structured pruning offers a promising solution by removing entire dimensions or layers,…

Machine Learning · Computer Science 2026-05-27 Jimyung Hong , Jaehyung Kim

Previous studies have demonstrated that not each sample in a dataset is of equal importance during training. Data pruning aims to remove less important or informative samples while still achieving comparable results as training on the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Zi Yang , Haojin Yang , Soumajit Majumder , Jorge Cardoso , Guillermo Gallego

In this paper, we present SwiftLearn, a data-efficient approach to accelerate training of deep learning models using a subset of data samples selected during the warm-up stages of training. This subset is selected based on an importance…

Structural pruning techniques are essential for deploying multimodal large language models (MLLMs) across various hardware platforms, from edge devices to cloud servers. However, current pruning methods typically determine optimal…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Zhihan Zhang , Xiang Pan , Hongchen Wei , Zhenzhong Chen

Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically…

Machine Learning · Computer Science 2019-12-10 Liangjian Wen , Xuanyang Zhang , Haoli Bai , Zenglin Xu

Large-scale neural models are increasingly trained with data pruning, synthetic data generation, cross-model distillation, reinforcement learning from human feedback (RLHF), and difficulty-based sampling. While several of these data-centric…

Machine Learning · Computer Science 2025-12-03 Yizhou Zhang , Lun Du

The choice of learning rate (LR) functions and policies has evolved from a simple fixed LR to the decaying LR and the cyclic LR, aiming to improve the accuracy and reduce the training time of Deep Neural Networks (DNNs). This paper presents…

Machine Learning · Computer Science 2022-10-25 Yanzhao Wu , Ling Liu

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model…

Machine Learning · Computer Science 2026-05-01 Nghia Bui , Lijing Wang

Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. Existing methods typically rely on Gumbel-Softmax to approximate discrete selection during training. However, the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Landi He , Mingde Yao , Shawn Young , Lijian Xu

The computational cost of training a vision-language model (VLM) can be reduced by sampling the training data. Previous work on efficient VLM pre-training has pointed to the importance of semantic data balance, adjusting the distribution of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Mingliang Liang , Zhuoran Liu , Arjen P. de Vries , Martha Larson

The extensive application of Large Language Models (LLMs) in generative coding tasks has raised concerns due to their high computational demands and energy consumption. Unlike previous structural pruning methods designed for classification…

Software Engineering · Computer Science 2025-04-25 Guang Yang , Yu Zhou , Xiangyu Zhang , Wei Cheng , Ke Liu , Xiang Chen , Terry Yue Zhuo , Taolue Chen

With the rapid development of deep learning, the sizes of neural networks become larger and larger so that the training and inference often overwhelm the hardware resources. Given the fact that neural networks are often over-parameterized,…

Machine Learning · Computer Science 2022-06-20 Zhangheng Li , Tianlong Chen , Linyi Li , Bo Li , Zhangyang Wang

We propose a novel parameter-efficient training (PET) method for large language models that adapts models to downstream tasks by optimizing a small subset of the existing model parameters. Unlike prior methods, this subset is not fixed in…

Computation and Language · Computer Science 2024-11-14 Felix Stahlberg , Jared Lichtarge , Shankar Kumar

Neural Networks (NN), although successfully applied to several Artificial Intelligence tasks, are often unnecessarily over-parametrised. In edge/fog computing, this might make their training prohibitive on resource-constrained devices,…

Machine Learning · Computer Science 2022-01-20 Lorenzo Valerio , Franco Maria Nardini , Andrea Passarella , Raffaele Perego
‹ Prev 1 4 5 6 7 8 10 Next ›