检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hu, Yuxuan Zhang, Jing Chen, Xiaodong Zhao, Zhe Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Engineering Research Center of Database and Business Intelligence Beijing China Tencent AI Lab Beijing China

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms. Despite these successes, such approaches suffer from an increased memory and computation overhead, which affects efficiency of LoRA methods. In response to this limitation, we introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs. To mitigate the substantial memory and computation demands associated with preserving sparsity, our approach incorporates strategies of weight recompute and computational graph rearrangement. In addition, we also improve the effectiveness of LoRS through better adapter initialization. These innovations lead to a notable reduction in memory and computation consumption during the fine-tuning phase, all while achieving performance levels that outperform existing LoRA approaches. © 2025, CC BY.

关键词： Problem oriented languages

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fast Cell Association Scheme Based on Deep Q-Learning in Ultra-Dense Cellular Networks

引用

China Communications 2021年第2期18卷 259-270页

作者： Jinhua Pan Lusheng Wang Hai Lin Zhiheng Zha Caihong Kai Key Laboratory of Knowledge Engineering with Big Data Ministry of Education.School of Computer Science and Information EngineeringHefei University of TechnologyHefei 230601China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei 230601China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education.School of Cyber Science and EngineeringWuhan UniversityWuhan 430072China

To support dramatically increased traffic loads,communication networks become *** cell association(CA)schemes are timeconsuming,forcing researchers to seek fast *** paper proposes a deep Q-learning based scheme,whose main idea is to train a deep neural network(DNN)to calculate the Q values of all the state-action pairs and the cell holding the maximum Q value is *** the training stage,the intelligent agent continuously generates samples through the trial-anderror method to train the DNN until *** the application stage,state vectors of all the users are inputted to the trained DNN to quickly obtain a satisfied CA result of a scenario with the same BS locations and user *** demonstrate that the proposed scheme provides satisfied CA results in a computational time several orders of magnitudes shorter than traditional ***,performance metrics,such as capacity and fairness,can be guaranteed.

关键词： ultra-dense cellular networks(UDCN) cell association(CA) deep Q-learning proportional fairness Q-learning

来源：评论

学校读者我要写书评

暂无评论

Maritime Unmanned Rescue System-of-Systems Design based on Attention Transformer

Maritime Unmanned Rescue System-of-Systems Design based on A...

引用

2024 IEEE International Conference on Unmanned Systems, ICUS 2024

作者： Ding, Wei Ming, Zhenjun Wang, Guoxin Yan, Yan van Beek, Anton Zhan, Hongfei School of Mechanical Engineering Beijing Institute of Technology Beijing China Yangtze Delta Region Academy of Beijing Institute of Technology Zhejiang China Key Laboratory of Industry Knowledge & Data Fusion Technology and Application Ministry of Industry and Information Technology Beijing China School of Mechanical and Materials Engineering University College Dublin Dublin Ireland Shanghai Aircraft Design and Research Institute Shanghai China

ISBN: (纸本)9798350384185

When natural or man-made disasters occur at sea, a maritime unmanned rescue system-of-systems (MURSoSs), as an important guarantee for the safety of people's lives and property, has a rapid response to emergency rescue services. In the design process of MURSoSs, it is often faced with problems such as unexplainable mechanisms and inaccurate modeling due to the characteristics of multi-level coupling and irregular emergence. A design method of MURSoSs based on an attention Transformer is proposed. First, this paper decomposes the MURSoSs into a multi-level organizational structure composed of individual performance, group structure, and overall effectiveness. Second, the maritime unmanned rescue simulation environment is constructed, to obtain the multi-level evolution data of group structure and overall effectiveness under different individual performance, and the attention Transformer is used to mine the functional correlation relationship between levels. Finally, the experimental simulation prediction is carried out by using this function relationship. Taking the design of MURSoSs as an example, the results show that the constructed model accurately quantifies the correlation relationship between levels and effectively reveal the internal logic of the emergence process of maritime rescue. © 2024 IEEE.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

On eigenvalues of a high-dimensional Kendall's rank correlation matrix with dependence

引用

Science China Mathematics 2023年第11期66卷 2615-2640页

作者： Zeng Li Cheng Wang Qinwen Wang Department of Statistics and Data Science Southern University of Science and TechnologyShenzhen 518055China School of Mathematical Sciences Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Scientific and Engineering Computing(Shanghai Jiao Tong University) Shanghai 200240China School of Data Science Fudan UniversityShanghai 200433China

In this paper,we investigate the limiting spectral distribution of a high-dimensional Kendall’s rank correlation *** underlying population is allowed to have a general dependence *** result no longer follows the generalized Marcenko-Pastur law,which is brand *** is the first result on rank correlation matrices with *** applications,we study Kendall’s rank correlation matrix for multivariate normal distributions with a general covariance *** these results,we further gain insights into Kendall’s rank correlation matrix and its connections with the sample covariance/correlation matrix.

关键词： Hoeffding decomposition Kendall's rank correlation matrix limiting spectral distribution random matrix theory

来源：评论

学校读者我要写书评

暂无评论

Accelerating local SGD for non-IID data using variance reduction

引用

Frontiers of Computer Science 2023年第2期17卷 73-89页

作者： Xianfeng LIANG Shuheng SHEN Enhong CHEN Jinchang LIU Qi LIU Yifei CHENG Zhen PAN Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230027China Ant Financial Services Group Hangzhou 310000China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China

Distributed stochastic gradient descent and its variants have been widely adopted in the training of machine learning models,which apply multiple workers in *** them,local-based algorithms,including Local SGD and FedAvg,have gained much attention due to their superior properties,such as low communication cost and ***,when the data distribution on workers is non-identical,local-based algorithms would encounter a significant degradation in the convergence *** this paper,we propose Variance Reduced Local SGD(VRL-SGD)to deal with the heterogeneous *** extra communication cost,VRL-SGD can reduce the gradient variance among workers caused by the heterogeneous data,and thus it prevents local-based algorithms from slow convergence ***,we present VRL-SGD-W with an effectivewarm-up mechanism for the scenarios,where the data among workers are quite *** from eliminating the impact of such heterogeneous data,we theoretically prove that VRL-SGD achieves a linear iteration speedup with lower communication complexity even if workers access non-identical *** conduct experiments on three machine learning *** experimental results demonstrate that VRL-SGD performs impressively better than Local SGD for the heterogeneous data and VRL-SGD-W is much robust under high data variance among workers.

关键词： distributed optimization variance reduction local SGD federated learning non-IID data

来源：评论

学校读者我要写书评

暂无评论

Classification of Table Cells Based on LLM Prompts

Classification of Table Cells Based on LLM Prompts

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Mengjie Liu Chenyang Bu Shengxing Bai Bingbing Dong Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Tables, as an important means of data storage, are widely used in spreadsheets, web tables, and PDFs. By integrating information from table data with knowledge re-trieved from an external knowledge base, and examining the correspondences between cell values in the table and instances in the knowledge base, we can extract knowledge from the table to augment and enrich the knowledge base. To achieve this goal, we first need to classify table cells based on their functions in the layout. Due to the diverse structures arising from the arrangements of rows and columns, as well as the complexity of content resulting from concise data storage, current automation techniques heavily rely on stylistic features of table cells, such as font or color. Moreover, these methods are rarely experimented with or validated on tables without style features. Recent literature indicates that large language models (LLMs) demonstrate an ability to understand the structure and content of tables in tasks such as table judgment reasoning. Even without extensive feature inputs or pre-training, LLMs still show comparable results to machine learning and deep learning in these tasks. Therefore, this paper attempts to apply LLMs to table cell classification without using other stylistic features. We have designed a 4-component prompt paradigm (Classification Definition, Instruction, Table, Com-pletion), representing respectively the classification definition, task instructions, table data, and result output. We conduct experiments on three datasets CIUS, SAUS, and DEEX for table cell classification with one-shot learning. Our experimental results show that with the assistance of LLMs, better results can be achieved without utilizing stylistic features.

关键词： Deep learning Image color analysis Large language models knowledge based systems Layout Memory One shot learning Benchmark testing Probability density function data mining

来源：评论

学校读者我要写书评

暂无评论

key Clues Guided Video Character Social Relationship Recognition Enhanced by LLM

Key Clues Guided Video Character Social Relationship Recogni...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Dong, Wenlong Zhu, Qing Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

ISBN: (纸本)9798350368741

Video Character Social Relationship Recognition (VCSRR) requires a comprehensive consideration about spatio-temporal and multi-modal clues in videos. Most existing methods mainly focus on integrating multi-modal clues and modeling interactions among characters. However, they fail to discover key clues in the complex video data or fully understand the clues related to social relationships. In this article, we propose a novel Large Language Model Enhanced key Clues Selection (LEKCS) framework to address the aforementioned issues. The core of LE-KCS is to mine multi-scale key clues from the perspectives of time, space and multi-modality, then transfer the knowledge about social relationships of the Large Language Model to VCSRR for understanding the selected clues. We evaluated LEKCS on the MovieGraphs dataset and the experimental results indicate that our proposed LE-KCS achieves state-of-the-art performance. © 2025 IEEE.

关键词： large language model Social relationship recognition video understanding

来源：评论

学校读者我要写书评

暂无评论

Phase prediction for high-entropy alloys using generative adversarial network and active learning based on small datasets

引用

Science China(Technological Sciences) 2023年第12期66卷 3615-3627页

作者： CHEN Cun ZHOU HengRu LONG WeiMin WANG Gang REN JingLi Henan Academy of Big Data School of Mathematics and StatisticsZhengzhou UniversityZhengzhou 450001China State Key Laboratory of Advanced Brazing Filler Metals and Technology Zhengzhou Research Institute of Mechanical EngineeringZhengzhou 450001China Institute of Materials Shanghai UniversityShanghai 200444China

In this paper,a new machine learning(ML)model combining conditional generative adversarial networks(CGANs)and active learning(AL)is proposed to predict the body-centered cubic(BCC)phase,face-centered cubic(FCC)phase,and BCC+FCC phase of high-entropy alloys(HEAs).Considering the lack of data,CGANs are introduced for data augmentation,and AL can achieve high prediction accuracy under a small sample size owing to its special sample selection ***,we propose an ML framework combining CGAN and AL to predict the phase of *** arithmetic optimization algorithm(AOA)is introduced to improve the artificial neural network(ANN).AOA can overcome the problem of falling into the locally optimal solution for the ANN and reduce the number of training *** AOA-optimized ANN model trained by the AL sample selection strategy achieved high prediction accuracy on the test *** improve the performance and interpretability of the model,domain knowledge is incorporated into the feature ***,considering that the proposed method can alleviate the problem caused by the shortage of experimental data,it can be applied to predictions based on small datasets in other fields.

关键词： high-entropy alloys phase prediction machine learning conditional generative adversarial networks active learning

来源：评论

学校读者我要写书评

暂无评论

IF-Font: Ideographic Description Sequence-Following Font Generation 38

IF-Font: Ideographic Description Sequence-Following Font Gen...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Xinping Ke, Xiao Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TS-Net: Two-stage deformable medical image registration network based on new smooth constraints

引用

Magnetic Resonance Imaging 2023年第1期99卷 26-33页

作者： Song, Lei Ma, Mingrui Liu, Guixia College of Computer Science and Technology Jilin University Jilin Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun 130012 China

Medical image registration can establish the spatial consistency of the corresponding anatomical structures between different medical images, which is important in medical image analysis. In recent years, with the rapid development of deep learning, the image registration methods based on deep learning greatly improve the speed, accuracy, and robustness of registration. Regrettably, these methods typically do not work well for large deformations and complex deformations in the image, and neglect to preserve the topological properties of the image during deformation. Aiming at these problems, we propose a new network TS-Net that learns deformation from coarse to fine and transmits information of different scales in the two stages. Two-stage network learning deformation from coarse to fine can gradually learn the large and complex deformations in images. In the second stage, the feature maps downsampled in the first stage for skip connection can expand the local receptive field and obtain more local information. The smooth constraints function used in the past is to impose the same restriction on the global, which is not targeted. In this paper, we propose a new smooth constraints function for each voxel deformation, which can better ensure the smoothness of the transformation and maintain the topological properties of the image. The experiments on brain datasets with complex deformations and heart datasets with large deformations show that our proposed method achieves better results while maintaining the topological properties of deformations compared to existing deep learning-based registration methods. © 2023 Elsevier Inc.

关键词： CNN Deformable image registration Smooth loss Two stage Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：