检索结果-内蒙古大学图书馆

Layer-Wise Learning Rate Optimization for Task-Dependent Fine-Tuning of Pre-Trained Models: An Evolutionary Approach

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第4期4卷 1-23页

作者： Bu, Chenyang Liu, Yuxin Huang, Manzong Shao, Jianxuan Ji, Shengwei Luo, Wenjian Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Artificial Intelligence and Big Data Hefei University Hefei China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

The superior performance of large-scale pre-Trained models, such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-Trained Transformer (GPT), has received increasing attention in both academic and industrial research and has become one of the current research hotspots. A pre-Trained model refers to a model trained on large-scale unlabeled data, whose purpose is to learn general language representation or features for fine-Tuning or transfer learning in subsequent tasks. After pre-Training is complete, a small amount of labeled data can be used to fine-Tune the model for a specific task or domain. This two-stage method of "pre-Training+fine-Tuning"has achieved advanced results in natural language processing (NLP) tasks. Despite widespread adoption, existing fixed fine-Tuning schemes that adapt well to one NLP task may perform inconsistently on other NLP tasks given that different tasks have different latent semantic structures. In this article, we explore the effectiveness of automatic fine-Tuning pattern search for layer-wise learning rates from an evolutionary optimization perspective. Our goal is to use evolutionary algorithms to search for better task-dependent fine-Tuning patterns for specific NLP tasks than typical fixed fine-Tuning patterns. Experimental results on two real-world language benchmarks and three advanced pre-Training language models show the effectiveness and generality of the proposed framework. © 2024 held by the owner/author(s).

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An empirical investigation of the older adults' continuance intention towards SNSs

An empirical investigation of the older adults' continuance ...

引用

作者： Liu, Wei Jiangxi Key Laboratory of Data and Knowledge Engineering Institute of Information Resources Management School of Information Technology Jiangxi University of Finance and Economics Nanchang360013 China

Although Social Network Services (SNSs) continuance usage has recently emerged as an important issue in information systems adaption, the research into older adults' continuance intention towards SNS is still very low, and the acceptance-discontinuance anomaly phenomenon (i.e. users discontinue using e-learning after initially accepting it) is a common occurrence. This study joins the perceived risk and perceived enjoyment to our prior research model which integrated the Expectation-Confirmation Model (ECM), the Technology Acceptance Model (TAM) and the Theory of Planned Behaviour (TPB) to hypothesise a theoretical model to explain and predict the older adults' intentions to continue using SNSs. The hypothesised model is validated empirically using a sample collected from 320 older adults who had prior experience with SNSs and was tested against the proposed research model using structure equation modelling. The results demonstrate that satisfaction has the most significant effect on older adults' continuance intention, followed by perceived usefulness, perceived risk, subject norm and perceived behavioural control. The results of these findings for SNSs practitioners are discussed at the end of this work. © Copyright 2016 Inderscience Enterprises Ltd.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

A mandatory access control model based on concept lattice

A mandatory access control model based on concept lattice

引用

International Conference on Network Computing and Information Security (NCIS)

作者： Zhang, Lei Zhang, Hongli Yin, Lihua Shen, Xiajiong School of Computer Science and Technology Harbin Institute of Technology Harbin China Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Data and Knowledge Engineering Henan University Kaifeng China

ISBN: (纸本)9780769543550

Confidentiality and integrity of information are basic attributes of information security, but the existing access control models cannot unify the both well. A mandatory access control model based on access control concept lattice is proposed in this paper. This model integrates many safe sensitivity labels such as integrity, confidentiality, security category. Thus, mandatory constraints of the access of subject to the object can be realized, and Hasse diagram of lattice can be created automatically, such that security levels of the subject and object in the system can be displayed clearly. © 2011 IEEE.

关键词： Access control models

来源：评论

学校读者我要写书评

暂无评论

Semantic Web mining and the representation, analysis, and evolution of Web space

Semantic Web mining and the representation, analysis, and ev...

引用

International Workshop on Representation and Analysis of Web Space, RAWS 2005

作者： Berendt, Bettina Hotho, Andreas Stumme, Gerd Institute of Information Systems Humboldt University Berlin 10 78 Berlin Germany Knowledge and Data Engineering Group University of Kassel D-34121 Kassel Germany

Semantic Web Mining aims at combining the two fast-developing research areas Semantic Web and Web Mining. This survey analyzes the convergence of trends from both areas: Growing numbers of researchers work on improving the results of Web Mining by exploiting semantic structures in the Web, and they use Web Mining techniques for building the Semantic Web. Last but not least, these techniques can be used for mining the Semantic Web itself. The second aim of this paper is to use these concepts to circumscribe what Web space is, what it represents and how it can be represented and analyzed. This is used to sketch the role that Semantic Web Mining and the software agents and human agents involved in it can play in the evolution of Web space.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Extracting commuter-specific destination hotspots from trip destination data-comparing the boro taxi service with Citi Bike in NYC

引用

Geo-Spatial Information Science 2020年第2期23卷 141-152页

作者： Andreas Keler Jukka M.Krisp Linfang Ding Department of Civil Geo and Environmental EngineeringTechnical University of MunichMunichGermany Applied Geoinformatics Institute of GeographyUniversity of Augsburg(UniA)AugsburgGermany The KRDB Research Centre for Knowledge and Data Free University of Bozen-BolzanoBozen-BolzanoItaly Department of Cartography Technical University of MunichMunichGermany

Taxi trajectories from urban environments allow inferring various information about the transport service qualities and commuter *** is possible to associate starting and end points of taxi trips with requirements of individual groups of people and even social *** research shows that due to service restrictions,boro taxis have typical customer destination locations on selected Saturdays:many drop-off clusters appear near the restricted zone,where it is not allowed to pick up customers and only few drop-off clusters appear at complicated *** crossings imply recent infrastructural *** want to follow up on these results and add one additional group of commuters:Citi Bike *** selected Saturdays in June 2015,we want to compare the destinations of boro taxi and Citi Bike *** is challenging due to manifold differences between active mobility and motorized road users,and,due to the fact that station-based bike sharing services are restricted to *** and end points of trips,as well as the volumes in between rely on specific numbers of bike sharing ***,we introduce a novel spatiotemporal assigning procedure for areas of influence around static bike sharing stations for extending available computational methods.

关键词： Urban transportation spatial analysis mobility patterns boro taxis vehicle fleets bicycle-sharing service

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Health Care Expense Anticipation using Computational Intelligence 1

Performance Analysis of Health Care Expense Anticipation usi...

引用

1st International Conference on Innovative engineering Sciences and Technological Research, ICIESTR 2024

作者： Gopalakrishnan, A. Kumarganesh, S. Divya Bharathi, G. Anthoniraj, S. Natarajan, Suresh Kumar Gochhait, Saikat Knowledge Institute of Technology Department of Artificial Intelligence and Data Science Salem India Knowledge Institute of Technology Department of Electronics and Communication Engineering Salem India Mahendra Institute of Technology Department of Computer Science and Engineering Namakkal India School of Computer Science and Engineering Ramanagara India Symbiosis International Deemed University Symbiosis Institute of Digital and Telecom Management Maharashtra Pune India

ISBN: (纸本)9798350348637

The escalating costs of healthcare globally necessitate the development of accurate prediction models to address the financial strain on individuals, families, businesses, and governments. This research employs linear regression models to forecast healthcare expenditures, analyzing the intricate relationship between various factors and costs. A comprehensive literature survey explores topics such as the impact of environmental pollution on healthcare spending, prediction of surgical expenses, budget impact analysis for cancer treatment, and the integration of big data in healthcare infrastructure investments. The methodology involves gathering a diverse dataset encompassing patient demographics, medical history, treatment methods, and associated expenditures. Exploratory data analysis employs Pearson's correlation coefficient to identify trends and correlations between variables. Two linear regression models are proposed and compared, with the second model excluding non-significant variables for enhanced accuracy and interpretability. Results indicate that the second model, with refined feature selection, outperforms the first in terms of mean squared error and R-squared values. A comparative analysis of different studies underscores the diverse findings in healthcare economics, ranging from the impact of CO2 emissions on health to predicting surgery costs and budgetary savings in cancer treatment. The research contributes to the growing body of knowledge in healthcare economics, providing decision-makers with a valuable tool for precise expenditure estimation. The emphasis on linear regression models aids stakeholders in understanding factors influencing healthcare costs, guiding resource allocation, policy creation, and financial planning for more sustainable and effective healthcare systems. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Multicomponent Similarity Graphs for Cross-Network Node Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1411-1424页

作者： Zhang, Yuhong Shi, Congmei Li, Xinzheng Zhang, Zan Hu, Xuegang School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei230009 China

Cross-network node classification aims to train a classifier for an unlabeled target network using a source network with rich labels. In applications, the degree of nodes mostly conforms to the long-tail distribution, i.e., most nodes in the network are tail nodes with sparse neighborhoods. The established methods focus on either the discrepancy cross network or the long tail in a single network. As for the cross-network node classification under long tail, the coexistence of sparsity of tail nodes and the discrepancy cross-network challenges existing methods for long tail or methods for the cross-network node classification. To this end, a multicomponent similarity graphs for cross-network node classification (MS-CNC) is proposed in this article. Specifically, in order to address the sparsity of the tail nodes, multiple component similarity graphs, including attribute and structure similarity graphs, are constructed for each network to enrich the neighborhoods of the tail nodes and alleviate the long-tail phenomenon. Then, multiple representations are learned from the multiple similarity graphs separately. Based on the multicomponent representations, a two-level adversarial model is designed to address the distribution difference across networks. One level is used to learn the invariant representations cross network in view of structure and attribute components separately, and the other level is used to learn the invariant representations in view of the fused structure and attribute graphs. Extensive experimental results show that the MS-CNC outperforms the state-of-the-art methods. Impact Statement-Node classification is an important task in graph mining. With the unavailability of labels, some researchers propose cross-network node classification, using one labeled network to assist the node classification of another unlabeled network. However, the long-tail of nodes leads to unsatisfactory performance and challenges the recent cross-network node classification m

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Fuzzy associative classifier for probabilistic numerical data 7

Fuzzy associative classifier for probabilistic numerical dat...

引用

7th International Conference on Intelligent Systems and knowledge engineering, ISKE 2012 with 1st International Conference on Cognitive Systems and Information Processing, CSIP 2012

作者： Pei, Bin Zhao, Tingting Zhao, Suyun Chen, Hong Key Laboratory of Data Engineering and Knowledge Engineering MOE Beijing China School of Information Renmin University of China Beijing China New Star Research Institute of Applied Tech Hefei China

ISBN: (纸本)9783642378287

Recently, a number of advanced data collection and processing methodologies have led to the proliferation of uncertain data. When discovering from such uncertain data, we should handle these uncertainties with caution, because classical mining algorithms may not be appropriate for uncertain tasks. This paper proposes a generic framework of fuzzy associative classifier for probabilistic numerical data, which is prevalent in the real-world applications, such as sensor networks and GPS-based location. In this paper, we first introduce an Aprioribased algorithm for mining fuzzy association rules from a probabilistic numerical dataset based on novel support and confidence measures suitable for such dataset. Then, we give fuzzy rules redundancy pruning strategy and database coverage method to build a compact fuzzy associative classifier in removing redundant rules and thus improving the accuracy of the classifier. We also redefine multiple fuzzy rules classification method for classifying new instances. Extensive experimental results show the effectiveness and efficiency of our algorithm. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Fuzzy rules

来源：评论

学校读者我要写书评

暂无评论

User needs for enhanced engagement with cultural heritage collections

User needs for enhanced engagement with cultural heritage co...

引用

2nd International Conference on Theory and Practice of Digital Libraries, TPDL 2012

作者： Sweetnam, Mark S. Agosti, Maristella Orio, Nicola Ponchia, Chiara Steiner, Christina M. Hillemann, Eva-Catherine Ó Siochrú, Micheál Lawless, Séamus Department of History Trinity College Dublin Ireland Department of Information Engineering University of Padua Italy Department of Cultural Heritage University of Padua Italy Knowledge Management Institute Graz University of Technology Austria Knowledge and Data Engineering Group Trinity College Dublin Ireland

ISBN: (纸本)9783642332890

This paper presents research carried out in order to elicit user needs for the design and development of a digital library and research platform intended to enhance user engagement with cultural heritage collections. It outlines a range of user constituencies for this digital library. The paper outlines a taxonomy of intended users for this system and describes in detail the characteristics and requirements of these users for the facilitation and enhancement of their engagement with and use of textual and visual cultural artefacts. © 2012 Springer-Verlag.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

The Processing and Improvement of Multi-Statement Queries in Chiql

引用

Journal of Computer Science & Technology 1998年第2期13卷 161-173页

作者：孟小峰黄锦辉叶孙民林耀燊王珊 Institute of Data and Knowledge Engineering College of Information Renmin University of China Beijing P.R. China Institute of Computing Technology Chinese Academy of Sciences Beijing P.R. China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Shatin N.T. Hong Kong

Chiql is a novel Chinese relational database query language for Chinese users. It supports procedural query style in which users can specify a complex database request in multiple simple statements. This facility renders Chiql simple-to-use and easy-toremember. However, direct execution of multi-statement Chiql queries (i.e. statement by statement) is often inefficient as potential indexbased operations (e.g. join) are by-passed. Furthermore, it often incurs additional database operations, such as scan and projection. To improve this situation, the SMA (Statement Merging Algorithm) is proposed. The goal of SMA is to merge as many dependent statements within a Chiql query as possible to form a more efficient Chiql query. The ability in achieving improved efficiency without sacrificing the simplicity of the language is the major advantage of this algorithm.

关键词： Chiql SQL query processing DBMS

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：