检索结果-内蒙古大学图书馆

CUTE: A Collaborative Fusion Representation-Based Fine-Tuning and Retrieval Framework for Code Search 19th

CUTE: A Collaborative Fusion Representation-Based Fine-Tunin...

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Song, Qihong Liu, Jianxun Hu, Haize School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Key Laboratory of Knowledge Processing and Networked Manufacturing Hunan University of Science and Technology Hunan Xiangtan China

ISBN: (纸本)9783031545207

Code search aims at searching semantically related code snippets from the large-scale database based on a given natural descriptive query. Fine-tuning pre-trained models for code search tasks has recently emerged as a new trend. However, most studies fine-tune models merely using metric learning, overlooking the beneficial effect of the collaborative relationship between code and query. In this paper, we introduce an effective fine-tuning and retrieval framework called CUTE. In the fine-tuning component, we propose a Collaborative Fusion Representation (CFR) consisting of three stages: pre-representation, collaborative representation, and residual fusion. CFR enhances the representation of code and query, considering token-level collaborative features between code and query. Furthermore, we apply augmentation techniques to generate vector-level hard negative samples for training, which further improves the ability of the pre-trained model to distinguish and represent features during fine-tuning. In the retrieval component, we introduce a two-stage retrieval architecture that includes pre-retrieval and refined ranking, significantly reducing time and computational resource consumption. We evaluate CUTE with three advanced pre-trained models on CodeSearchNet consisting of six programming languages. Extensive experiments demonstrate the fine-tuning effectiveness and retrieval efficiency of CUTE. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Developing new Mg alloy as potential bone repair material via constructing weak anode nano-lamellar structure

引用

Journal of Magnesium and Alloys 2023年第1期11卷 154-175页

作者： Jinshu Xie Lele Wang Jinghuai Zhang Liwei Lu Zhi Zhang Yuying He Ruizhi Wu Key Laboratory of Superlight Material and Surface Technology Ministry of EducationCollege of Materials Science and Chemical EngineeringHarbin Engineering UniversityHarbin150001China School of Materials Science and Engineering Hunan University of Science and TechnologyXiangtan411201China

The mechanics-corrosion and strength-ductility tradeoffs of magnesium(Mg)alloys have limited their applications in fields such as orthopedic ***,a fine-grain structure consisting of weak anodic nano-lamellar solute-enriched stacking faults(SESFs)with the average thickness of 8 nm and spacing of 16 nm is constructed in an as-extruded Mg96.9Y1.2Ho1.2Zn0.6Zr0.1(at.%)alloy,obtaining a high yield strength(YS)of 370 MPa,an excellent elongation(EL)of 17%,and a low corrosion rate of 0.30 mm y−1(close to that of high-pure Mg)in a uniform corrosion *** scanning Kelvin probe force microscopy(SKPFM),one-dimensional nanostructured SESFs are identified as the weak anode(∼24 mV)for the first *** excellent corrosion resistance is mainly related to the weak anodic nature of SESFs and their nano-lamellar structure,leading to the more uniform potential distribution to weaken galvanic corrosion and the release of abundant Y^(3+)/Ho^(3+)from SESFs to form a more protective film with an outer Ca_(10)(PO_(4))_(6)(OH)_(2)/Y_(2)O_(3)/Ho_(2)O_(3) layer(thickness percentage of this layer:72.45%).For comparison,the as-cast alloy containing block 18R long period stacking ordered(LPSO)phase and the heat-treated alloy with fine lamellar 18R-LPSO phase(thickness:80 nm,spacing:120 nm)are also studied,and the characteristics of SESFs and 18R-LPSO phase,such as the weak anode nature of the former and the cathode nature of the latter(37-90 mV),are distinguished under the same alloy ***,we put forward the idea of designing Mg alloys with high mechanical and anti-corrosion properties by constructing"homogeneous potential strengthening microstructure",such as the weak anode nano-lamellar SESFs structure.

关键词： Mg alloys Corrosion Solute-enriched stacking faults LPSO structure SKPFM Hydroxyapatite

来源：评论

学校读者我要写书评

暂无评论

Stress effect on lattice thermal conductivity of anode material NiNB_(2)O_(6)for lithium-ion batteries

引用

Chinese Physics B 2023年第5期32卷 43-48页

作者：陈奥童话吴成伟谢国锋谢忠祥向长青周五星 School of Materials Science and Engineering&Hunan Provincial Key Laboratory of Advanced Materials for New Energy Storage and Conversion Hunan University of Science and TechnologyXiangtan 411201China School of Science Hunan Institute of TechnologyHengyang 421002China College of Information Science and Engineering Jishou UniversityJishou 416000China

The thermal transport properties of NiNB_(2)O_(6)as anode material for lithium-ion battery and the effect of strain were studied by machine learning interatomic potential combined with Boltzmann transport *** results show that the lattice thermal conductivity of NiNB_(2)O_(6)along the three crystal directions[100],[010],and[001]are 0.947 W·m^(-1)·K^(-1),0.727 W·m^(-1)·K^(-1),and 0.465 W·m^(-1)·K^(-1),respectively,indicating the anisotropy of the lattice thermal conductivity of NiNB_(2)O_(6).This anisotropy of the lattice thermal conductivity stems from the significant difference of phonon group velocities in different crystal directions of NiNB_(2)O_(6).When the tensile strain is applied along the[001]crystal direction,the lattice thermal conductivity in all three directions ***,when the compressive strain is applied,the lattice thermal conductivity in the[100]and[010]crystal directions is increased,while the lattice thermal conductivity in the[001]crystal direction is abnormally reduced due to the significant inhibition of compressive strain on the group *** indicate that the anisotropy of thermal conductivity of NiNB_(2)O_(6)can be enhanced by the compressive strain,and reduced by the tensile strain.

关键词： nickel niobate lattice thermal conductivity uniaxial strain machine learning potential

来源：评论

学校读者我要写书评

暂无评论

RLSM: A Strategy Matrix based Microservice Splitting Method for Reinforcement Learning

RLSM: A Strategy Matrix based Microservice Splitting Method ...

引用

2024 International Conference on Intelligent Systems and Robotics, CISR 2024

作者： Liu, Yuqiang Yu, Jianyong Han, Xue Liu, Yuqi The School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China The School of Hunan Software Vocational and Technical University Xiangtan China

We introduce a novel microservice splitting approach, the Policy Matrix-based Reinforcement Learning Splitting Method (RLSM), designed to overcome the limitations of traditional service splitting schemes by providing a solution that is both fine-grained and efficient, with a strong emphasis on automation. This method utilizes dynamic link tracking and static code analysis techniques to analyze business modules, and extract entities using data flow graphs. We use these entities as agents in reinforcement learning to construct a reinforcement learning environment model, and optimize and update the value of entities by constructing a policy matrix, replacing the Q table in traditional Q-learning algorithms. Finally, we obtained a set of entity categories and used the K-means algorithm to cluster the entities of these categories, with each clustered cluster being a split individual microservice. The experimental results show that this splitting scheme not only achieves automated splitting, but also maintains a stable compliance rate of about 97% for microservices. This is enough to demonstrate that RLSM is more efficient and flexible in completing service design and evaluation. © Published under licence by IOP Publishing Ltd.

关键词： Data flow graphs

来源：评论

学校读者我要写书评

暂无评论

Web API Recommendation via Combining Adaptive Multichannel Graph Representation and xDeepFM Quality Prediction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 3218-3232页

作者： Cao, Buqing Qing, Yueying Zhou, Dong Xie, Xiang Kang, Guosheng Liu, Jianxun Fletcher, Kenneth K. Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan411201 China Guangdong University of Foreign Studies School of Information Science and Technology Guangzhou510420 China University of Massachusetts Computer Science BostonMA02125-3393 United States

With the increasing number of Web services, how to provide developers with Web APIs that meet their Mashup requirements accurately and efficiently has become a challenge. Even though the existing methods show improvements in service recommendation, the efficiency and accuracy (ACC) of them still need to be improved due to their limited representation in fuzing network topology and node feature of Web service, and the neglected higher-order feature interactions of Web service. To address this problem, this article proposes a Web APIs recommendation method via combining adaptive multichannel (AMC) graph representation and eXtreme deep factorization machine (xDeepFM) quality prediction. In this method, firstly, specific embedding and shared embedding in Web API node isomorphic network are extracted from the nodes' feature space, topology space, and the combination of the two spaces. Then, attention mechanism is used to adaptively learn the importance weight of each embedding. Next, these embeddings are adaptively integrated to generate the multichannel graph representation of Web APIs for service classification. Finally, aiming at the Web APIs in the service cluster, it utilizes xDeepFM to model and mine the complex feature interactions and predict and rank the scores of Web APIs for Mashup creation. The experimental results on the real datasets of ProgrammableWeb show that compared with DeepFM, wide and deep learning (WDL), FM supported neural network (FNN), neural factorization machine (NFM), and mixed logistic regression (MLR), the method proposed in this article has an average improvement in AUC of 2.3%, 7.9%, 8.0%, 9.6%, and 13.3%. © 2020 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

A Code Search Method Incorporating Code Annotations 19th

A Code Search Method Incorporating Code Annotations

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Li, Qi Liu, Jianxun Zhang, Xiangping School of Computer Science and Engineering Hunan University of Science and Technology Hunan Xiangtan411201 China Hunan Key Lab for Services Computing and Novel Software Technology Hunan University of Science and Technology Hunan Xiangtan411201 China

ISBN: (纸本)9783031545207

Code search is a technique for users to retrieve code snippets from the Code base using natural language, which is dedicated to retrieve the target code accurately and quickly to improve the efficiency of software development. The deep learning based code search technique greatly improves the accuracy of search by learning the relationship between code and query statements. Since it relies on the extracted code features, acquiring more code features is the key to quickly improve the search performance. However, most of the previous works have not taken code annotations into consideration. In this paper, we take code annotations as code features and apply them to code search, which is named ICA-CS (Code Search that Incorporates Code Annotations). In the method, firstly, the code features are embedded to get the corresponding vector representation. It is then processed by bidirectional LSTM (Long Short-Term Memory) network or multi-head attention respectively, followed by features fusion. And finally, the model is trained by joint embedding and using the minimised ranking loss function. As the experimental results show, on the evaluation metric MRR (mean reciprocal rank) compared to the state-of-the-art models DeepCS, SAN-CS, CARLCS-CNN and SelfAtt, the proposed model improves 48.96%, 17.11%, 41.01% and 13.07%, respectively. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Experimental Research on a Feasible Building Insulation Material Based Reed in China

引用

Journal of Thermal science 2025年第1期34卷 176-187页

作者： LIU Tiantian PENG Yizhe LIU Lifang CAI Chenghan WANG Shuang LI Hongqiang College of Civil Engineering Hunan UniversityChangsha 410082China College of Civil Engineering Hunan University of Science and TechnologyXiangtan 411201China School of Energy and Power Jiangsu University of Science and TechnologyZhenjiang 212100China National Center for International Research Collaboration in Building Safety and Environment(NCIRCBSE) Hunan UniversityChangsha 410082China Key Laboratory of Building Safety and Energy Efficiency of the Ministry of Education Hunan UniversityChangsha 410082China

The seemingly useless reeds are prepared as thermal insulation materials,which not only meet the requirements of environmental sustainability but also enhance the added value of reeds,creating new economic *** hydrophobicity of raw biomass surfaces leads to problems such as weak bonding strength and non-dense structure in the formed materials,as well as issues related to the residual insect infestations on the *** this study,reed straw was used as the raw material,and foamed geopolymer was used as the binder to prepare building insulation materials based *** improve the interfacial adhesion performance between reed straw and foamed geopolymer,a thermochemical modification method-thermal carbonization,was *** this study,the mechanical properties and hydraulic properties of the studied materials with different degrees of surface thermal modification were tested,especially the fire resistance performance,and weathering resistance performance rarely found in published *** the surface thermal modification condition of reed straw was 250℃(30 min),the comprehensive performance of reed-based building insulation materials was the best,when the studied material density was 321.3 kg/m^(3);the compressive strength was 0.59 MPa;the thermal conductivity was 0.101 W/(m·K);the pH was 11.27;the moisture absorption rate was 25.1%,and the compressive strength loss rate in wet-dry cycles was 18.5%.In addition,it had excellent fire resistance performance and weathering resistance *** new material can be widely used to improve the thermal insulation of traditional buildings and as sandwich filler in prefabricated buildings,such as preparing insulating walls.

关键词： pre-treatment of reeds interface adhesion properties building insulation material based reed fire resistance performance weathering resistance performance

来源：评论

学校读者我要写书评

暂无评论

An Approach for Privacy-Aware Mobile App Package Recommendation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6240-6252页

作者： Liu, Shanpeng Cao, Buqing Liu, Jianxun Kang, Guosheng Shi, Min Li, Xiong Fletcher, Kenneth K. Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan411201 China Hunan University of Technology School of Computer Zhuzhou412007 China Harvard University Harvard Medical School BostonMA02138 United States School of Computer Science and Engineering Chengdu611731 China University of Massachusetts School of Computer Science BostonMA02125 United States

With the prosperity of the mobile Internet, the abundance of data makes it difficult for users to choose their favorite app. Thus, mobile app recommendation as an emerging topic attracts lots of attention. However, existing methods for app recommendation rarely consider recommendation accuracy under the privacy representation of user preferences. To address this problem, we propose a privacy-aware app package recommendation method named APP-Rec. Specifically, in this method: 1) treat an app and its associated heterogeneous entities (APP-Rec considers not only the apps themselves but also a variety of related factors-collectively referred to as heterogeneous entities, such as app category and app neighbors) as an app package and extract comprehensive features from the app package using an intrapackage attention network and an interpackage attention network to improve app recommendation;and 2) design a privacy module utilizing Laplace noise to achieve privacy preservation of user preferences. Experimental results show that APP-Rec outperforms the state-of-the-art methods in terms of area under the curve (AUC). Moreover, the privacy preservation of user preferences in APP-Rec is proved by theoretical analysis and experimental results. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Code Completion Approach Combining Pointer Network and Transformer-XL Network 19th

A Code Completion Approach Combining Pointer Network and Tr...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zhang, Xiangping Liu, Jianxun Long, Teng Hu, Haize School of Computer Science and Engineering Hunan University of Science and Technology Hunan Xiangtan411100 China Hunan Key Lab. for Services Computing and Novel Software Technology Hunan University of Science and Technology Hunan Xiangtan411100 China

ISBN: (纸本)9783031545207

Code completion is an integral component of modern integrated development environments, as it not only facilitates the software development process but also enhances the quality of software products. By leveraging large-scale codes to learn the probability distribution among code token units, deep learning methods have demonstrated significant improvements in the accuracy of token unit recommendations. However, the effectiveness of code completion with deep learning techniques is hindered by information loss. To alleviate the above problem, we proposed a code language model which combines the pointer network and Transformer-XL network to overcome the limitations of existing approaches in code completion. The proposed model takes as input the original code fragment and its corresponding abstract syntax tree and leverages the Transformer-XL model as the basis model for capturing long-term dependencies. Furthermore, we integrate a pointer network as a local component to predict the out-of-vocabulary words. The proposed method is evaluated on real PY150 and JS150 datasets. The comparative experimental results demonstrate the effectiveness of our model in improving the accuracy of the code completion task at the token unit level. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

An Efficient Virtual Channel Scheme Based on Multi-hop Payment Channel 10

An Efficient Virtual Channel Scheme Based on Multi-hop Payme...

引用

10th IEEE International Conference on Cyber Security and Cloud Computing and 9th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Li, Feng Liu, Yaqin Liang, Wei Xie, Songyou Yang, Yang Li, Yuhui Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan China Hunan University College of Computer Science and Electronic Engineering Changsha China

ISBN: (纸本)9798350312461

The transaction throughput and confirmation time of the current mainstream blockchain cryptocurrency platform are far lower than those of traditional centralized trading platforms, which is difficult to meet the growing needs of users. Therefore, this paper proposes an efficient multi-hop off-chain Virtual Channel (VC) payment scheme to improve the confirmation speed of transactions by performing high-frequency and small transactions off-chain. The proposed scheme constructs a virtual channel scheme with dynamic selection [1], [2] through Hash Time-Lock Contract (HTLC) and constant collateral, and closes the virtual channel through on-chain settlement to ensure the balance security and atomicity of transactions. The proposed VC scheme is suitable for multi-hop Payment Channel (PC) networks, after the VC construction is completed, the transaction initiator and receiver directly conduct transactions through the virtual channel, ensuring the privacy of the transaction. Experimental analysis shows that the proposed scheme can resist a variety of malicious attacks and realize a rapid and safe transaction process. © 2023 IEEE.

关键词： Network security

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：