检索结果-内蒙古大学图书馆

GTE: learning code AST representation efficiently and effectively

Science China(Information Sciences) 2025年第3期68卷 393-394页

作者： Yihao QIN Shangwen WANG Bo LIN Kang YANG Xiaoguang MAO College of Computer Science and Technology National University of Defense Technology Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology

With the development of deep learning in recent years, code representation learning techniques have become the foundation of many software engineering tasks such as program classification [1] and defect detection. Earlier approaches treat the code as token sequences and use CNN, RNN, and the Transformer models to learn code representations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ForkXplorer:an approach of fork summary generation

引用

Frontiers of Computer Science 2022年第2期16卷 1-15页

作者： Zhang ZHANG Xinjun MAO Chao ZHANG Yao LU Key Laboratory of Software Engineering for Complex Systems College of ComputerNational University of Defense TechnologyChangsha 410073China

Pull-based development has become an important paradigm for distributed software *** this model,each developer independently works on a copied repository(i.e.,a fork)from the central *** is essential for developers to maintain awareness of the state of other forks to improve collaboration *** this paper,we propose a method to automatically generate a summary of a *** first use the random forest method to generate the label of a fork,i.e.,feature implementation or a bug *** on the information of the fork-related commits,we then use the TextRank algorithm to generate detailed activity information of the ***,we apply a set of rules to integrate all related information to construct a complete fork *** validate the effectiveness of our method,we conduct 30 groups of manual experiment and 77 groups of case studies on *** propose Fea_(avg)to evaluate the performance of Fea_(avg)the generated fork summary,considering the content accuracy,content integrity,sentence fluency,and label extraction *** results show that the average of of the fork summary generated by this method is *** than 63%of project maintainers and the contributors believe that the fork summary can improve development efficiency.

关键词： open source software pull-based development fork summary distributed cooperative development

来源：评论

学校读者我要写书评

暂无评论

Relay Selection and Power Control for Mobile Underwater Acoustic Communication Networks: A Dual-Thread Reinforcement Learning Approach

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2024年第2期9卷 1-1页

作者： Dai, Jun Li, Xinbin Han, Song Yu, Junzhi Liu, Zhixin Key Lab of Industrial Computer Control Engineering of Hebei Province China Department of Advanced Manufacturing and Robotics College of Engineering State Key Laboratory for Turbulence and Complex Systems Peking University Beijing China

This paper deals with a cooperation communication problem (relay selection and power control) for mobile underwater acoustic communication networks. To achieve satisfactory transmission capacity, we propose a reinforcement-learning-based cooperation communication scheme to efficiently resist the highly dynamic communication links and strongly unknown time-varying channel states caused by the mobility of Autonomous Underwater Vehicles (AUVs). Firstly, a particular Markov decision process is developed to model the dynamic relay selection process of mobile AUV in the unknown scenario. In the developed model, an experimental statistical-based partition mechanism is proposed to cope with the greatly increasing dimension of the state space caused by the mobility of AUV, reducing the search optimization difficulty. Secondly, a dual-thread reinforcement learning structure with actual and virtual learning threads is proposed to efficiently track the superior relay action. In the actual learning thread, the proposed improved probability greedy policy enables the AUV to strengthen the exploration for the reward information of potential superior relays on the current state. Meanwhile, in the virtual learning thread, the proposed upper-confidence-bound-index-based uncertainty estimation method can estimate the action-reward level of historical states. Consequently, the combination of actual and virtual learning threads can efficiently obtain satisfactory Q value information, thereby making superior relay decision-making in a short time. Thirdly, a power control mechanism is proposed to reuse the current observed action-reward information and transform the multiple unknown parameter nonlinear joint power optimization problem into a convex optimization problem, thereby enhancing network transmission capacity. Finally, simulation results verify the effectiveness of the proposed scheme. IEEE

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Complementary Learning System Based Intrinsic Reward in Reinforcement Learning 48

Complementary Learning System Based Intrinsic Reward in Rein...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Gao, Zijian Xu, Kele Jia, Hongda Wan, Tianjiao Ding, Bo Feng, Dawei Mao, Xinjun Wang, Huaimin National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems Changsha China

ISBN: (纸本)9781728163277

Deep reinforcement learning has achieved encouraging performance in many realms. However, one of its primary challenges is the sparsity of extrinsic rewards, which is still far from solved. Complementary learning system theory suggests that effective human learning relies on two complementary learning systems utilizing short-term and long-term memories. Inspired by the fact that humans evaluate curiosity by comparing current observations with historical information, we propose a novel intrinsic reward, namely CLS-IR, which aims to address the problems caused by sparse extrinsic rewards. Specifically, we train a self-supervised predictive model with short-term and long-term memories via exponential moving averages. We employ the information gain between the two memories as the intrinsic reward, which does not incur additional training costs but leads to better exploration. To investigate the effectiveness of CLS-IR, we conduct extensive experimental evaluations;the results demonstrate that CLS-IR can achieve state-of-the-art performance on Atari games and DeepMind Control Suite. © 2023 IEEE.

关键词： complementary learning system Deep reinforcement learning exploration intrinsic reward

来源：评论

学校读者我要写书评

暂无评论

Progressive Diversifying Policy for Multi-Agent Reinforcement Learning 48

Progressive Diversifying Policy for Multi-Agent Reinforcemen...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Sun, Shaoqi Zhai, Yuanzhao Xu, Kele Feng, Dawei Ding, Bo National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems Changsha China

ISBN: (纸本)9781728163277

Multi-Agent Reinforcement Learning (MARL) has recently achieved promising performance in many collaborative decision making tasks. However, one of the main bottleneck challenges for MARL is the sparsity of the team reward, which can lead to the homogenization of agents' behaviors. To address these issues, we propose a Progressive Diversifying Policy (PDP) algorithm in this paper. Specifically, we propose to actively amplify the diversity between agents' policies during learning and exploit diversity as an additional intrinsic reward for MARL. Furthermore, we propose a progressive diversity boosting policy to find a better team policy. Leveraging the aforementioned improvements, our method can handle sparse team rewards and alleviate the homogeneous behaviors of agents. We conduct experiments on widely-used MARL environments and the results show that PDP can provide state-of-the-art performance while maintaining a competitive convergence speed. © 2023 IEEE.

关键词： Homogeneous behavior Multi-agent reinforcement learning Policy diversity Sparse reward

来源：评论

学校读者我要写书评

暂无评论

Diversifying Message Aggregation in Multi-Agent Communication Via Normalized Tensor Nuclear Norm Regularization 48

Diversifying Message Aggregation in Multi-Agent Communicatio...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhai, Yuanzhao Xu, Kele Ding, Bo Feng, Dawei Gao, Zijian Wang, Huaimin National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems Changsha China

ISBN: (纸本)9781728163277

The use of graph attention networks (GAT) in communication-enhanced multi-agent reinforcement learning (Comm-MARL) has become prevalent. While successful, GAT can lead to homogeneity in the strategies of message aggregation, which can severely limit multi-agent coordination. To address this challenge, we study the adjacency tensor of the communication graph. Then we define a new nuclear tensor rank and its convex surrogate, the normalized tensor nuclear norm to measure the homogeneity of message aggregation. Leveraging the norm, we further propose a plug-and-play regularizer on the adjacency tensor, named Normalized Tensor Nuclear Norm Regularization (NTNNR), to actively enrich the diversity of message aggregation during the training stage. NTNNR is agnostic to specific Comm-MARL algorithms and can be flexibly integrated with different graph-attention methods. Empirical results demonstrate that aggregating messages using NTNNR-enhanced GAT can improve the efficiency of the training and achieve higher asymptotic performance than existing message aggregation methods. © 2023 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Recommending Missed Citations Identified by Reviewers: A New Task, Dataset and Baselines 30

Recommending Missed Citations Identified by Reviewers: A New...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Long, Kehan Li, Shasha Wang, Pancheng Bao, Chenlong Tang, Jintao Wang, Ting School of Computer National University of Defense Technology China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China

ISBN: (纸本)9782493814104

Citing comprehensively and appropriately has become a challenging task with the explosive growth of scientific publications. Current citation recommendation systems aim to recommend a list of scientific papers for a given text context or a draft paper. However, none of the existing work focuses on already included citations of full papers, which are imperfect and still have much room for improvement. In the scenario of peer reviewing, it is a common phenomenon that submissions are identified as missing vital citations by reviewers. This may lead to a negative impact on the credibility and validity of the research presented. To help improve citations of full papers, we first define a novel task of Recommending Missed Citations Identified by Reviewers (RMC) and construct a corresponding expert-labeled dataset called CitationR. We conduct an extensive evaluation of several state-of-the-art methods on CitationR. Furthermore, we propose a new framework RMCNet with an Attentive Reference Encoder module mining the relevance between papers, already-made citations, and missed citations. Empirical results prove that RMC is challenging, with the proposed architecture outperforming previous methods in all metrics. We release our dataset and benchmark models to motivate future research on this challenging new task. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Paper

来源：评论

学校读者我要写书评

暂无评论

Cloud-Edge-End Collaboration for the Finishing Rolling System: An Accelerated Data-driven Cooperative Distributed Predictive Control Approach 13

Cloud-Edge-End Collaboration for the Finishing Rolling Syste...

引用

13th IEEE Data Driven Control and Learning systems Conference, DDCLS 2024

作者： He, Zhichen Liang, Dingguo Yang, Ying College of Engineering Peking University State Key Lab for Turbulence and Complex Systems Department of Mechanics and Engineering Science Beijing100871 China

ISBN: (纸本)9798350361674

In this brief, an accelerated data-driven cooperative distributed predictive control approach with the cloud-edge-end collaboration implemented is proposed for the finishing rolling system(FRS) of the hot strip mill process. Specifically, in the end device, the operating data of the rolling mill stands and looper systems are collected and uploaded to the cloud server, which contributes to satisfying the interconnected information communication requirements for optimization problem-solving. Then, the control optimization problem is quickly solved in the cloud server, where the cooperative distributed solving method is applied, and an accelerated iteration strategy is adopted. Moreover, a regularized optimization technique is used to suppress the interference of disturbance and noise. Thus, the edge device can set the input of the bottom-level control to realize the control of the finishing rolling system with the optimal control sequences sent from the cloud server. Finally, simulations on a real finishing rolling system are conducted to illustrate the effectiveness of the proposed method. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Urban Traffic Control Meets Decision Recommendation System:A Survey and Perspective

引用

IEEE/CAA Journal of Automatica Sinica 2024年第10期11卷 2043-2058页

作者： Qingyuan Ji Xiaoyue Wen Junchen Jin Yongdong Zhu Yisheng Lv Zhejiang Lab Hangzhou 311121China College of Engineering and Architecture Zhejiang UniversityHangzhou 310013China College of Electrical Engineering Zhejiang UniversityHangzhou 310013China the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE

Urban traffic control is a multifaceted and demanding task that necessitates extensive decision-making to ensure the safety and efficiency of urban transportation *** approaches require traffic signal professionals to manually intervene on traffic control devices at the intersection level,utilizing their knowledge and ***,this process is cumbersome,labor-intensive,and cannot be applied on a large network *** studies have begun to explore the applicability of recommendation system for urban traffic control,which offer increased control efficiency and *** a decision recommendation system is complex,with various interdependent components,but a systematic literature review has not yet been *** this work,we present an up-to-date survey that elucidates all the detailed components of a recommendation system for urban traffic control,demonstrates the utility and efficacy of such a system in the real world using data and knowledgedriven approaches,and discusses the current challenges and potential future directions of this field.

关键词： Recommendation system traffic control traffic perception traffic prediction

来源：评论

学校读者我要写书评

暂无评论

AST: Annulus Swin Transformer For Pedestrians Detection Under Top-view Fisheye Image 12

AST: Annulus Swin Transformer For Pedestrians Detection Unde...

引用

12th International Conference on Computing and Pattern Recognition, ICCPR 2023

作者： Lu, Cheng Wei, Xuan Lu, Xiaobo School of Software Engineering Southeast University Suzhou China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Suzhou China School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9798400707988

Fisheye images have a larger field of view than ordinary perspective cameras and can obtain more scene information. Therefore, object detection based on top-view fisheye images has wide applications in security monitoring, passenger flow perception, and industrial detection fields. However, due to the radial distortion symmetry of fisheye images, most current networks still need to adapt to this radial distortion symmetry. Therefore, we proposed the Annulus Swin Transformer(AST) for top-view fisheye images, which includes Annulus Window (AW) and Annulus Position Coding (APC). Traditional rectangular windows can break the radial distortion symmetry in top-view fisheye images, instead of taking advantage of it to improve the network's perception of distortion. Annulus-Window transforms it into an inner-to-outer annulus window to calculate self-attention, thereby maintaining the distortion symmetry of the fisheye image within each window, allowing the network to perceive better the degree of distortion in the fisheye image and get better detection performance. Due to the varying degree of distortion of images within each annulus, APC introduces an annulus position to work with Annulus window based on the original position encoding, enabling it to contain annulus position information. The experimental results on the dataset SEU-fisheye show that our method improves the neural network's performance markedly. © 2023 ACM.

关键词： Image enhancement

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：