检索结果-内蒙古大学图书馆

Towards On-The-Fly Code Performance Profiling

ACM Transactions on Software Engineering and Methodology 1000年

作者： Xing Hu Weixin Lin Zhuang Liu Xin Xia Michael Ling Yuan Wang David Lo School of Software Technology Zhejiang University China College of Computer Science and Technology Zhejiang University China Zhejiang University China Huawei Technologies Canada Canada Huawei Sweden Research Center Sweden School of Computing and Information Systems Singapore Management University Singapore

Improving the performance of software applications is one of the most important tasks in software evolution and maintenance. In the Intel Microarchitecture, CPUs employ pipelining to utilize resources as effectively as possible. Some types of software patterns or algorithms can have implications on the underlying CPU pipelines and result in inefficiencies. Therefore, analyzing how well the CPU’s pipeline(s) are being utilized while running an application is important in software performance analysis. Existing techniques, such as Intel VTune Profiler, usually detect software performance issues from CPU pipeline metrics after the software enters production and during the running time. These techniques require developers to manually analyze monitoring data and perform additional test runs to obtain relevant information about performance problems. It costs a lot of time and human effort for developers to build, deploy, test, execute, and monitor the *** alleviate these problems, we propose a novel approach named PGProf to predict the CPU pipeline before execution and provide the profiling feedback during the development process. PGProf exploits the graph neural networks to learn semantic and structural representations for C functions and then predict the fraction of pipeline slots in each category for them during the development process. Given a code snippet, we fuse different types of code structures, e.g., Abstract Syntax Tree (AST), data Flow Graph (DFG), and Control Flow Graph (CFG) into one program graph. During offline learning, we first leverage the gated graph neural network to capture representations of C functions. PGProf then automatically estimates the final pipeline values according to the learned semantic and structural features. For online prediction, we predict pipeline metrics with four category values by leveraging the offline trained model. We build our dataset from C projects in GitHub and use Intel VTune profiler to get profiling information

关键词： Program Graphs Performance Profiling CPU utilization Graph Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Rough Sets and Intelligent systems Paradigms 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Marzena Kryszkiewicz Zbigniew W. Raś Chris Cornelis Davide Ciucci Jesús Medina-Moreno Hiroshi Motoda

ISBN: (数字)9783319087290

ISBN: (纸本)9783319087283

This book constitutes the refereed proceedings of the 23rd Australasian Joint Conference on Rough Sets and Intelligent systems Paradigms, RSEISP 2014, held in Granada and Madrid, Spain, in July 2014. RSEISP 2014 was held along with the 9th International Conference on Rough Sets and Current Trends in computing, RSCTC 2014, as a major part of the 2014 Joint Rough Set Symposium, JRS 2014. JRS 2014 received 40 revised full papers and 37 revised short papers which were carefully reviewed and selected from 120 submissions and presented in two volumes. This volume contains the papers accepted for the conference RSEISP 2014, as well as the three invited papers presented at the conference. The papers are organized in topical sections on plenary lecture and tutorial papers; foundations of rough set theory; granular computing and covering-based rough sets; applications of rough sets; induction of decision rules - theory and practice; knowledge discovery; spatial data analysis and spatial databases; information extraction from images.

关键词： Artificial Intelligence data Mining and Knowledge Discovery Mathematical Logic and Formal Languages information systems Applications (incl. Internet) information Storage and Retrieval Pattern Recognition

来源：评论

学校读者我要写书评

暂无评论

database systems for Advanced Applications 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Bonghee Hong Xiaofeng Meng Lei Chen Werner Winiwarter Wei Song

ISBN: (数字)9783642402708

ISBN: (纸本)9783642402692

This book constitutes the workshop proceedings of the 18th International Conference on database systems for Advanced Applications, DASFAA 2013, held in Wuhan, China, in April 2013. The volume contains three workshops, each focusing on specific area that contributes to the main themes of the DASFAA conference: The First International Workshop on Big data Management and Analytics (BDMA 2013), the Third International Workshop on Social Networks and Social Web (SNSM 2013) and the International Workshop on Semantic computing and Personalization (SeCoP 2013).

关键词： information systems Applications (incl. Internet) Artificial Intelligence information Storage and Retrieval database Management computer Communication Networks data Mining and Knowledge Discovery

来源：评论

学校读者我要写书评

暂无评论

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning

引用

ACM Transactions on Software Engineering and Methodology 1000年

作者： Boyang Yang Haoye Tian Jiadong Ren Hongyu Zhang Jacques Klein Tegawende Bissyande Claire Le Goues Shunfu Jin School of Information Science and Engineering Yanshan University China School of Computing and Information Systems University of Melbourne Australia School of Big Data and Software Engineering Chongqing University China SnT University of Luxembourg Luxembourg School of Computer Science Carnegie Mellon University USA

Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair, we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective ➊), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective ➋). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality *** apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.

关键词： Program Repair Fine-tuning Large Language Model Open Source

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Image Analysis, Signal Processing and Telecommunications 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Riccardo Poli Hans-Michael Voigt Stefano Cagnoni David Corne George D. Smith Terence C. Fogarty

ISBN: (数字)9783540489177

ISBN: (纸本)9783540658375

This book consitutes the refereed joint proceedings of the First European Workshop on Evolutionary Computation in Image Analysis and Signal Processing, EvoIASP '99 and of the First European Workshop on Evolutionary Telecommunications, EuroEcTel '99, held in Göteborg, Sweden in May 1999. The 18 revised full papers presented were carefully reviewed and selected for inclusion in the volume. The book presents state-of-the-art research results applying techniques from evolutionary computing in the specific application areas.

关键词： Image Processing and computer Vision computer Communication Networks Communications Engineering, Networks

来源：评论

学校读者我要写书评

暂无评论

information Retrieval Technology 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Pu-Jen Cheng Min-Yen Kan Wai Lam Preslav Nakov

ISBN: (数字)9783642171871

ISBN: (纸本)9783642171864

The Asia information Retrieval Societies Conference (AIRS) 2010 was the sixth conference in the AIRS series,aiming to bring together international researchers and developers to exchange new ideas and the latest results in information - trieval. The scope of the conference encompassed the theory and practice of all aspects of information retrieval in text, audio, image, video, and multimedia data. AIRS 2010 continued the conference series that grew from the information Retrieval with Asian Languages (IRAL) workshop series, started in 1996. It has become a mature venue for information retrieval work, ?nding support from the ACM Special Interest Group on information Retrieval (SIGIR); the Association for Computational Linguistics and Chinese Language Processing (ACLCLP); ROCLING; and the information Processing Society of Japan, Special Interest GrouponinformationFundamentals andAccess Technologies(IPSJSIG-IFAT). This year saw a sharp rise in the number of submissions over the previous year. A total of 120 papers were submitted, representing work by academics and practitioners not only from Asia, but also from Australia, Europe, North America, etc. The high quality of the work made it di?cult for the dedicated *** adouble-blindreviewingprocess,26submissions(21%)wereacceptedasfulloral papers and 31 (25%) were accepted as short posters. The success of this conferencewas only possible with the support of allof the authorswho submitted papers for review, the programcommittee members who constructively assessedthe submissions, and the registered conference delegates. We thank them for their support of this conference, and for their long-term support of this Asian-centric venue for IR research and development.

关键词： database Management information Storage and Retrieval information systems Applications (incl. Internet) Algorithm Analysis and Problem Complexity data Structures data Storage Representation

来源：评论

学校读者我要写书评

暂无评论

Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing

引用

ACM computing Surveys 1000年

作者： Md Mehedi Hasan Moloud Abdar Abbas Khosravi Uwe Aickelin Pietro Lio Ibrahim Hossain Ashikur Rahman Saeid Nahavandi Institute for Intelligent Systems Research and Innovation Deakin University Geelong Australia Institute for Intelligent Systems Research and Innovation Deakin University Burwood Australia School of Computing and Information Systems The University of Melbourne Melbourne Australia Department of Computer Science and Technology Cambridge University Cambridge United Kingdom of Great Britain and Northern Ireland Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Swinburne University of Technology Melbourne Australia

Although neural networks (especially deep neural networks) have achieved better-than-human performance in many fields, their real-world deployment is still questionable due to the lack of awareness about the limitations in their knowledge. To incorporate such awareness in the machine learning model, prediction with reject option (also known as selective classification or classification with abstention) has been proposed in the literature. In this paper, we present a systematic review of the prediction with the reject option in the context of various neural networks. To the best of our knowledge, this is the first study focusing on this aspect of neural networks. Moreover, we discuss different novel loss functions related to the reject option and post-training processing (if any) of network output for generating suitable measurements for knowledge awareness of the model. Finally, we address the application of the rejection option in reducing the prediction time for real-time problems and present a comprehensive summary of the techniques related to the reject option in the context of a wide variety of neural networks. Our code is available on GitHub: https://***/MehediHasanTutul/Reject_option.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computational Methods in systems Biology 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： David Gilbert Monika Heiner

ISBN: (数字)9783642336362

ISBN: (纸本)9783642336355

This book constitutes the thoroughly refereed conference proceedings of the 10th International Conference on Computational Methods in systems Biology, CMSB 2012, held in London, UK, during October 3-5, 2012. The 17 revised full papers and 8 flash posters presented together with the summaries of 3 invited papers were carefully reviewed and selected from 62 submissions. The papers cover the analysis of biological systems, networks, and data ranging from intercellular to multiscale. Topics included high-performance computing, and for the first time papers on synthetic biology.

关键词： Computational Biology/Bioinformatics Computation by Abstract Devices Simulation and Modeling computer Appl. in Life sciences Software Engineering Symbolic and Algebraic Manipulation

来源：评论

学校读者我要写书评

暂无评论

When Fine-Tuning LLMs Meets data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair

引用

ACM Transactions on Software Engineering and Methodology 1000年

作者： Wenqiang Luo Jacky Keung Boyang Yang He Ye Claire Le Goues Tegawendé F. Bissyandé Haoye Tian Xuan Bach D. Le Department of Computer Science City University of Hong Kong China Jisuan Institute of Technology Beijing JudaoYouda Network Technology Co. Ltd. China School of Computer Science Carnegie Mellon University USA SnT University of Luxembourg Luxembourg School of Computing and Information Systems University of Melbourne Australia

Software systems have been evolving rapidly and inevitably introducing bugs at an increasing rate, leading to significant maintenance costs. While large language models (LLMs) have demonstrated remarkable potential in enhancing software development and maintenance practices, particularly in automated program repair (APR), they rely heavily on high-quality code repositories. Most code repositories are proprietary assets that capture the diversity and nuances of real-world industry software practices, which public datasets cannot fully represent. However, obtaining such data from various industries is hindered by data privacy concerns, as companies are reluctant to share their proprietary codebases. There has also been no in-depth investigation of collaborative software development by learning from private and decentralized data while preserving data privacy for program *** address the gap, we investigate federated learning as a privacy-preserving method for fine-tuning LLMs on proprietary and decentralized data to boost collaborative software development and maintenance. We use the private industrial dataset TutorCode for fine-tuning and the EvalRepair-Java benchmark for evaluation, and assess whether federated fine-tuning enhances program repair. We then further explore how code heterogeneity (i.e., variations in coding style, complexity, and embedding) and different federated learning algorithms affect bug fixing to provide practical implications for real-world software development collaboration. Our evaluation reveals that federated fine-tuning can significantly enhance program repair, achieving increases of up to 16.67% for Top@10 and 18.44% for Pass@10, even comparable to the bug-fixing capabilities of centralized learning. Moreover, the negligible impact of code heterogeneity implies that industries can effectively collaborate despite diverse data distributions. Different federated algorithms also demonstrate unique strengths across LLMs, suggesting that

关键词： Program Repair Federated Learning Large Language Models

来源：评论

学校读者我要写书评

暂无评论

Digital Library Applications 1

引用

丛书名： Synthesis Lectures on information Concepts, Retrieval, and Services

1000年

作者： Edward A. Fox Jonathan P. Leidig

ISBN: (数字)9783031022845

ISBN: (纸本)9783031011566

Digital libraries (DLs) have evolved since their launch in 1991 into an important type of information system, with widespread application. This volume advances that trend further by describing new research and development in the DL field that builds upon the 5S (Societies, Scenarios, Spaces, Structures, Streams) framework, which is discussed in three other DL volumes in this *** the 5S framework may be used to describe many types of information systems, and is likely to have even broader utility and appeal, we focus here on digital libraries. Drawing upon six (Akbar, Kozievitch, Leidig, Li, Murthy, Park) completed and two (Chen, Fouh) in-process dissertations, as well as the efforts of collaborating researchers, and scores of related publications, presentations, tutorials, and reports, this book demonstrates the applicability of 5S in five digital library application areas, that also have importance in the context of the WWW, Web 2.0, and innovative information systems. By integrating surveys of the state-of-the-art, newresearch, connections with formalization, case studies, and exercises/projects, this book can serve as a textbook for those interested in computing, information, and/or library science. Chapter 1 focuses on images, explaining how they connect with information retrieval, in the context of CBIR systems. Chapter 2 gives two case studies of DLs used in education, which is one of the most common applications of digital libraries. Chapter 3 covers social networks, which are at the heart of work onWeb 2.0, explaining the construction and use of deduced graphs, that can enhance retrieval and recommendation. Chapter 4 demonstrates the value of DLs in escience, focusing, in particular, on cyber-infrastructure for simulation. Chapter 5 surveys geospatial information in DLs, with a case study on geocoding. Given this rich content, we trust that any interested in digital libraries, or in related systems, will find this volume to be motivating, intellectu

关键词： information systems and Communication Service

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：