检索结果-内蒙古大学图书馆

IEEE International Conference on software Quality, Reliability and Security (QRS)

作者： Chaochao Shen Wenhua Yang Minxue Pan Yu Zhou College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China State Key Laboratory for Novel Software Technology Nanjing University China

In the realm of collaborative software development, version control systems (VCS) like Git play an indispensable role, enabling concurrent development and facilitating seamless integration of disparate code contributions. Despite these benefits, merge conflicts resulting from simultaneous changes to identical code lines often pose significant challenges to the integration process. Addressing this challenge, our paper introduces a novel two-stage approach, termed as CHATMERGE, for resolving Git merge conflicts. CHATMERGE pioneers a unique strategy that employs machine learning to initially predict resolution strategies, and subsequently leverages a large language model, ChatGPT, to create resolutions for conflicts that necessitate complex resolution strategies. A series of comprehensive experiments validate CHATMERGE’s efficacy, demonstrating its impressive alignment with historical manual resolutions and its superior performance relative to existing, publicly accessible tools. The paper further explores the influence of various classification algorithms and the prompt construction process for ChatGPT, providing further insights into the merge conflict resolution process. Moreover, to foster continued advancements in this area, CHATMERGE, along with its associated training and testing datasets, is made publicly available, offering a valuable resource for both developers and researchers. This work, therefore, provides both an innovative solution to merge conflict resolution and a strong foundation for future explorations in this domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An efficient split learning framework for recurrent neural network in mobile edge environment 22

An efficient split learning framework for recurrent neural n...

引用

2022 Conference on Research in Adaptive and Convergent Systems, RACS 2022

作者： Zhou, Wenxuan Qu, Zhihao Zhao, Yanchao Tang, Bin Ye, Baoliu Key Laboratory of Water Big Data Technology of Ministry of Water Resources and School of Computer and Information Hohai University Jiangsu Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China

ISBN: (纸本)9781450393980

Split learning is an emerging distributed machine learning paradigm that exhibits great advantages in privacy protection and training efficiency. Most previous studies pay attention to client-server based split learning on Convolutional Neural networks (CNNs), and little effort has been spent on investigating the Recurrent Neural Networks (RNNs) oriented split learning. To fill in this gap, we propose a multi-hop split learning algorithm for RNN in mobile edge computing, namely M-SLRNN. The core idea is to efficiently orchestrate resource-constrained mobile devices to collaboratively train a large-size model. We formulate the optimization problem with the objective of minimizing the total training time and theoretically analyze its hardness. Then, we propose an efficient algorithm that conditionally has an approximation ratio of 2. Extensive experiments on both image and text classification tasks demonstrate the effectiveness and the efficiency of the proposed algorithm. © 2022 ACM.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep User and Item Inter-matching Network for CTR Prediction 28th

Deep User and Item Inter-matching Network for CTR Predicti...

引用

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Yuan, Zhiyang Xiao, Yingyuan Yang, Peilin Hao, Qingbo Wang, Hongya Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China College of Computer Science and Engineering Donghua University Shanghai China

ISBN: (纸本)9783031306716

CTR prediction plays an important role in increasing company revenue and user experience, and many efforts start with historical behavior to uncover user interest. There are two main problems with previous works: (1) When most previous works mined interests from users’ historical behaviors, they only focus on implicit or explicit interests. (2) When most previous works mined user interests through the relationship between target users and similar users, the representation of target users was not rich and accurate enough, resulting in less accurate item recommendations. Therefore the Deep User and Item Inter-Matching Network (DUIIN) is proposed in this paper to solve the above problems. First, we design Item-to-Item Network (IIN), using two different sub-networks Evolving Interest Network (EIN) and Feature Interaction Network (FIN) to mine the hidden interests and explicit interests shown by users’ historical behaviors, respectively. Then the User-to-User Network (UUN) is designed to mine user interests through the relationship between target users and similar users after representing the target users more accurately and richly. The experimental results show that the DUIIN model proposed in this paper performs better than other state-of-the-art models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

TCB Intrusion Detection Method Based on Data Enhancement 10th

TCB Intrusion Detection Method Based on Data Enhancement

引用

10th International Conference of Pioneering computer Scientists, Engineers and Educators, ICPCSEE 2024

作者： Ye, Yunlong Zhou, Lin Hu, Xiaobo Wang, Yong Department of Computer Science and Technology Shanghai University of Electric Power Shanghai China State Grid Key Laboratory of Power Industrial Chip Design and Analysis Technology Beijing Smart-Chip Microelectronics Technology Co. Ltd. Beijing China

ISBN: (纸本)9789819787456

Within the online sphere, intrusion detection technology plays an increasingly vital role in safeguarding our information security. The current research on intrusion detection mainly focuses on two aspects: machine learning and deep learning, but it cannot be ignored that data balance also affects the efficiency of intrusion detection. The vast majority of current datasets are imbalanced, and during the training process, the model ignores a few class samples, which affects the efficiency of intrusion detection. Therefore, in response to this issue, this article introduces a novel intrusion detection model that integrates Transformer and CNN-BiLSTM, leveraging WGAN-enhanced data. This model first uses Transformer for global capture, establishes global connections, then uses CNN-BiLTM to capture spatial and temporal features, and finally uses Softmax classifier for classification. The dataset used in this article is NSL-KDD. The experimental results show that after data balance processing, the accuracy of two classification tasks of TCB model reaches 92.19%, which is at least 2.24% higher than other models, and the accuracy of multi classification tasks reaches 82.94%, which is at least 1.03% higher than other models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Attention Is All You Need for LLM-based Code Vulnerability Localization

arXiv

引用

arXiv 2024年

作者： Li, Yue Li, Xiao Wu, Hao Zhang, Yue Cheng, Xiuzhen Zhong, Sheng Xu, Fengyuan National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science Drexel University Philadelphia United States School of Computer Science and Technology Shandong University Qingdao China

The rapid expansion of software systems and the growing number of reported vulnerabilities have emphasized the importance of accurately identifying vulnerable code segments. Traditional methods for vulnerability localization, such as manual code audits or rule-based tools, are often time-consuming and limited in scope, typically focusing on specific programming languages or types of vulnerabilities. In recent years, the introduction of large language models (LLMs) such as GPT and LLaMA has opened new possibilities for automating vulnerability detection. However, while LLMs show promise in this area, they face challenges, particularly in maintaining accuracy over longer code contexts. This paper introduces LOVA, a novel framework leveraging the self-attention mechanisms inherent in LLMs to enhance vulnerability localization. Our key insight is that self-attention mechanisms assign varying importance to different parts of the input, making it possible to track how much attention the model focuses on specific lines of code. In the context of vulnerability localization, the hypothesis is that vulnerable lines of code will naturally attract higher attention weights because they have a greater influence on the model’s output. By systematically tracking changes in attention weights and focusing on specific lines of code, LOVA improves the precision of identifying vulnerable lines across various programming languages. Through rigorous experimentation and evaluation, we demonstrate that LOVA significantly outperforms existing LLM-based approaches, achieving up to a 5.3× improvement in F1-scores. LOVA also demonstrated strong scalability, with up to a 14.6× improvement in smart contract vulnerability localization across languages like C, Python, Java, and Solidity. Its robustness was proven through consistent performance across different LLM architectures. Copyright © 2024, The Authors. All rights reserved.

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

Integrating Dual Prototypes for Task-Wise Adaption in Pre-Trained Model-Based Class-Incremental Learning

arXiv

引用

arXiv 2024年

作者： Xu, Zhiming Yang, Suorong Xu, Baile Zhao, Jian Shen, Furao National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Department of Computer Science and Technology Nanjing University China

Class-incremental learning (CIL) aims to acquire new classes while conserving historical knowledge incrementally. Despite existing pre-trained model (PTM) based methods performing excellently in CIL, it is better to fine-tune them on downstream incremental tasks with massive patterns unknown to PTMs. However, using task streams for fine-tuning could lead to catastrophic forgetting that will erase the knowledge in PTMs. This paper proposes the Dual Prototype network for Task-wise Adaption (DPTA) of PTM-based CIL. For each incremental learning task, a task-wise adapter module is built to fine-tune the PTM, where the center-adapt loss forces the representation to be more centrally clustered and class separable. The dual prototype network improves the prediction process by enabling test-time adapter selection, where the raw prototypes deduce several possible task indexes of test samples to select suitable adapter modules for PTM, and the augmented prototypes that could separate highly correlated classes are utilized to determine the final result. Experiments on several benchmark datasets demonstrate the state-of-the-art performance of DPTA. The code is submitted in supplementary materials and will be open-sourced after the paper is published. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Understanding and Enhancing Issue Prioritization in GitHub

Understanding and Enhancing Issue Prioritization in GitHub

引用

IEEE International Conference on Automated software Engineering (ASE)

作者： Yingying He Wenhua Yang Minxue Pan Yasir Hussain Yu Zhou College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China State Key Laboratory for Novel Software Technology Nanjing University China

GitHub has become a prominent platform for open source software development, facilitating collaboration and communication among a diverse group of contributors. Efficient issue tracking is a crucial aspect of managing projects on GitHub, and labels serve as one of the primary mechanisms for issue prioritization, while various other issue features are also utilized by issue handlers for the same purpose. However, in large projects, prioritizing issues remains a challenge, and the efficacy of using labels or other issue features for prioritization is not well understood. To address this knowledge gap, we conduct a comprehensive empirical study that investigates the role of labels in GitHub issue prioritization, examines the influence of various issue features on prioritization, and assesses the performance of different ranking algorithms based on these impactful features. Our study, conducted on a dataset comprising data from over 1.5 million issues across diverse GitHub projects, provides valuable insights for issue handling in open source platforms and offers guidance for future research in this domain. Specifically, the study reveals the limited effectiveness of labels in issue prioritization, highlights the significance of certain issue features in the prioritization process, and compares the performance of various ranking algorithms for issue prioritization to support issue handlers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamical Trust Construction Schema with Fuzzy Decision in P2P Systems

引用

Chinese Journal of Electronics 2023年第3期18卷 417-421页

作者： Yang Wang Ruchuan Wang Zhijie Han College of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China Department of Computer Anhui Normal University Wuhu China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

The security problem for Peer-to-peer (P2P) systems has been gradually recognized as an important topic of P2P applications. Among existing solution for P2P security, how to establish trust relationship among peers is a key problem in demand. This paper proposes a novel dynamical trust construction schema based on fuzzy decision and Extended automated trust negotiation (EATN). The presented approach adopts fuzzy trust graph to describe the trust information in the P2P systems. Trust relationship among peers can be constructed by the combination of the fuzzy trust graph, fuzzy path search algorithm and EATN. The relevant application case indicates the schema is feasible. The simulations also show that the presented schema can improve the interactive success ratio by enhancing the trust relationship in the P2P systems.

关键词： Simulation Heuristic algorithms Education Telecommunication traffic Peer-to-peer computing Security Trust management

来源：评论

学校读者我要写书评

暂无评论

Joint Edge Aggregation and Association for Cost-Efficient Multi-Cell Federated Learning 42

Joint Edge Aggregation and Association for Cost-Efficient Mu...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Wu, Tao Qu, Yuben Liu, Chunsheng Jing, Yuqian Wu, Feiyu Dai, Haipeng Dong, Chao Cao, Jiannong National University of Defense Technology China Nanjing University of Aeronautics and Astronautics Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space China Nanjing University State Key Laboratory for Novel Software Technology China The Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong

ISBN: (纸本)9798350334142

Federated learning (FL) has been proposed as a promising distributed learning paradigm to realize edge artificial intelligence (AI) without revealing the raw data. Nevertheless, it would incur inevitable costs in terms of training latency and energy consumption, due to periodical communication between user equipments (UEs) and the geographically remote central parameter server. Thus motivated, we study the joint edge aggregation and association problem to minimize the total cost, where the model aggregation over multiple cells just happens at the network edge. After proving its hardness with complex coupled variables, we transform it into a set function optimization problem and prove the objective function is neither submodular nor supermodular, which further complicates the problem. To tackle this difficulty, we first split it into multiple edge association subproblems, where the optimal solution to the computation resource allocation can be efficiently obtained in the closed form. We then construct a substitute function with the supermodularity and provable upper bound. On this basis, we reformulate an equivalent set function minimization problem under a matroid base constraint. We then propose an approximation algorithm to the original problem based on the two-stage search strategy with theoretical performance guarantee. Both extensive simulations and field experiments are conducted to validate the effectiveness of our proposed solution. © 2023 IEEE.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

E-book with Animation Playing Capability Based on Liquid Crystal Display technology

E-book with Animation Playing Capability Based on Liquid Cry...

引用

SID International Symposium Digest of Technical Papers, 2023

作者： Liu, Pengcheng Tseng, Man-Chun Yeung, Fion Sze-Yan Kwok, Hoi-Sing State Key Laboratory of Advanced Displays and Optoelectronics Technologies Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Electronic ink (E-ink) displays have become increasingly popular in e-books due to their paper-like appearance, readability in direct sunlight, low power consumption, and flexible sizing. However, the slow switching speed of bistable LCDs and E-ink limits their ability to play animations. This paper proposes a novel method for fabricating fast-switching bistable liquid crystal displays capable of playing animations. The research is based on a new type of bistable LCD technology that achieves lower driving voltages than existing E-ink displays. The research team has significant experience developing bistable displays and has invented many new technologies in their laboratory. The proposed technology combines the benefits of bistable displays with the ability to play animations, a significant advancement in display technology. © 2023, John Wiley and Sons Inc. All rights reserved.

关键词： Animation

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：