检索结果-内蒙古大学图书馆

23rd International Semantic Web Conference, ISWC 2024

作者： Shao, Zhoutian Cui, Yuanning Hu, Wei State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China National Institute of Healthcare Data Science Nanjing University Nanjing210093 China

ISBN: (纸本)9783031778490

Knowledge graphs (KGs) are widely acknowledged as incomplete, and new entities are constantly emerging in the real world. Inductive KG reasoning aims to predict missing facts for these new entities. Among existing models, graph neural networks (GNNs) based ones have shown promising performance for this task. However, they are still challenged by inefficient message propagation due to the distance and scalability issues. In this paper, we propose a new inductive KG reasoning model, MStar, by leveraging conditional message passing neural networks (C-MPNNs). Our key insight is to select multiple query-specific starting entities to expand the scope of progressive propagation. To propagate query-related messages to a farther area within limited steps, we subsequently design a highway layer to propagate information toward these selected starting entities. Moreover, we introduce a training strategy called LinkVerify to mitigate the impact of noisy training samples. Experimental results validate that MStar achieves superior performance compared with state-of-the-art models, especially for distant entities. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Efficient Large Scale Reverse-time Migration Imaging Computation based on Distributed Spark Cluster with GPUs 21

Efficient Large Scale Reverse-time Migration Imaging Computa...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Wangzhang, Suhui Yang, Ruizhang Gu, Rong Li, Bo Liu, Dingjin Wang, Zhaokang Nanjing University State Key Laboratory for Novel Software Technology China Sinopec Geophysical Research Institute China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology China

ISBN: (纸本)9798350329223

The reverse-time migration (RTM) imaging algorithm, which is used for complex underground structure analysis, is known as one of the current mainstream method of high-precision seismic imaging. Nowadays, as the fast development of seismic data acquisition technology, there exists large amount of seismic data. Thus, the requirement for the efficient computation of the reverse-time migration (RTM) imaging algorithms over large-scale data have been increased greatly. To address this problem, in this paper, we propose a distributed reverse-time migration imaging algorithm based on the widely-used Spark platform first. Based on that, we design and implement a RTM computation solution based on Spark and GPU with several optimizations, including pre-shuffle&caching and load balancing. We also analyze the fault tolerance capability of the proposed distributed algorithm. We evaluate the proposed methods on the typical three-dimensional wavefild benchmark dataset. Experimental results show that the performance of the Spark based reverse-time migration imaging algorithm can scale up near linearly with computing nodes. In addition, the GPU+Spark based version has significant performance improvement on execution efficiency over the Spark-based algorithm. Moreover, the proposed optimization strategies also take effect. In addition, the method proposed in this paper has been applied in the real-world environment of one of the top oil exploration companies world wide, and has achieved significant improvement under the premise of the algorithm correctness guarantee. © 2023 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Towards Gradient Equalization and Feature Diversification for Long-Tailed Multi-Label Image Recognition

引用

IEEE Transactions on Multimedia 2025年 27卷 3489-3500页

作者： Chen, Zhao-Min Cui, Quan Zhang, Xiaoqin Deng, Ruoxi Xia, Chaoqun Lu, Shijian Nanjing University National Key Laboratory for Novel Software Technology Nanjing210093 China Waseda University Graduate School of Information Production and Systems Fukuoka169-8050 Japan Wenzhou University College of Computer Science and Artificial Intelligence Wenzhou325060 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

Multi-label image recognition with convolutional neural networks has achieved remarkable progress in the past few years. However, most existing multi-label image recognition methods suffer from the long-tailed data distribution problem, i.e., head categories occupy most training samples, while tailed classes have few samples. This work firstly studies the influence of long-tailed data distribution on existing multi-label image recognition methods. Based on this, two crucial issues of the existing methods are identified: 1) severe gradient imbalance between head and tailed categories, even though re-balancing strategies are adopted;2) the lack of diversity of tail category training samples. To tackle the first issue, this paper proposes a group sampling strategy to create group- wise balanced data distribution. Meanwhile, a dynamic gradient balancing loss is proposed to equalize the gradient for all categories. To tackle the second issue, this paper proposes a diversity enhancement module to fuse the information across all categories, preventing the network from overfitting tail classes. Furthermore, it also balances the gradient, promoting the discriminability of learned classifiers. Our method significantly outperforms the baseline method and achieves competitive performance with state-of-the-art methods on VOC-LT and COCO-LT datasets. Extensive ablation studies are conducted to verify the effectiveness of the essential proposals. © 1999-2012 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

On interleaving space exploration of multi-threaded programs

引用

Frontiers of computer science 2021年第4期15卷 17-28页

作者： Dongjie CHEN Yanyan JIANG Chang XU Xiaoxing MA State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China Department of Computer Science and Technology Nanjing UniversityNanjing 210023China

Exploring the interleaving space of a multithreaded program to efficiently detect concurrency bugs is important but also difficult because of the astronomically many thread *** paper presents a novel framework to decompose a thread schedule generator that explores the interleaving space into the composition of a basic generator and its extension under the“small interleaving hypothesis”.Under this framework,we in-depth analyzed research work on interleaving space exploration,illustrated how to design an effective schedule generator,and shed light on future research opportunities.

关键词： survey testing concurrency bugs interleaving space

来源：评论

学校读者我要写书评

暂无评论

SeeMe: An intelligent edge server selection method for location-aware business task computing over IIoT

SeeMe: An intelligent edge server selection method for locat...

引用

作者： Dou, Wanchun Liu, Bowen Duan, Jirun Dai, Fei Qi, Lianyong Xu, Xiaolong State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China School of Computer Science Qufu Normal University Qufu China School of Computer and Software Nanjing University of Information Science and Technology Nanjing China

In the past few years, latency-sensitive task computing over the industrial internet of things (IIoT) has played a key role in an increasing number of intelligent applications, such as intelligent self-driving vehicles and unmanned aircraft systems. The edge computing paradigm provides a basic functional infrastructure for across-domain business task computing on distributed edge servers. With this observation, a trade-off between the mobile devices and the fixed edge servers is needed to run moving task computing in a low-latency way. Given this challenge, an intelligent server selection method, named SeeMe, is proposed in this paper. Technically speaking, this method aims at minimizing the communication capacity and the transferring capacity in a multiobjective optimization way to find a low-latency edge server. The experiments and comparison analysis verify the availability of our method. © 2022 John Wiley & Sons Ltd.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Fast target-aware learning for few-shot video object segmentation

引用

science China(Information sciences) 2022年第8期65卷 71-86页

作者： Yadang CHEN Chuanyan HAO Zhi-Xin YANG Enhua WU Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and Technology School of Education Science and Technology Nanjing University of Posts and Telecommunications State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of Macau State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of Sciences Faculty of Science and Technology University of Macau

Few-shot video object segmentation(FSVOS) aims to segment a specific object throughout a video sequence when only the first-frame annotation is given. In this study, we develop a fast target-aware learning approach for FSVOS, where the proposed approach adapts to new video sequences from its firstframe annotation through a lightweight procedure. The proposed network comprises two models. First, the meta knowledge model learns the general semantic features for the input video image and up-samples the coarse predicted mask to the original image size. Second, the target model adapts quickly from the limited support set. Concretely, during the online inference for testing the video, we first employ fast optimization techniques to train a powerful target model by minimizing the segmentation error in the first frame and then use it to predict the subsequent frames. During the offline training, we use a bilevel-optimization strategy to mimic the full testing procedure to train the meta knowledge model across multiple video *** proposed method is trained only on an individual public video object segmentation(VOS) benchmark without additional training sets and compared favorably with state-of-the-art methods on DAVIS-2017, with a J &F overall score of 71.6%, and on YouT ubeVOS-2018, with a J &F overall score of 75.4%. Meanwhile,a high inference speed of approximately 0.13 s per frame is maintained.

关键词： video object segmentation few-shot target-aware meta knowledge bilevel-optimization

来源：评论

学校读者我要写书评

暂无评论

Credit assignment for trained neural networks based on Koopman operator theory

引用

Frontiers of computer science 2024年第1期18卷 251-253页

作者： Zhen LIANG Changyuan ZHAO Wanwei LIU Bai XUE Wenjing YANG Zhengbin PANG Institute for Quantum Information&State Key Laboratory of High Performance Computing National University of Defense TechnologyChangsha 410000China Institute of Software Chinese Academy of SciencesBeijing 100190China College of Computer Science and Technology National University of Defense TechnologyChangsha 410000China

1 Introduction Artificial neural networks(ANNs,also NNs)have recently emerged as leading candidate models for deep learning,popularly used in various areas[1–3].Behind the enormous success,ANNs are generally with complicated structures,there being an intricate data flow through multiple linear or nonlinear components between the input layer and the output ***,it is pressing to evaluate how much a specific component contributes to the final output,termed the Credit Assignment Problem(CAP)[4]in this paper.

关键词： layer assignment operator

来源：评论

学校读者我要写书评

暂无评论

A unified user behavior model for trajectory-based tasks with different types of path constraints

引用

science China(Information sciences) 2023年第10期66卷 316-318页

作者： Hao ZHANG Jin HUANG Huawei TU Feng TIAN Guozhong DAI Hongan WANG Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Department of Computer Science and Information Technology La Trobe University

An important research branch of human-computer interaction(HCI) is to develop predictive models for human performance in fundamental interactions [1]. On today's graphical user interface(GUI), users often implicitly perform various trajectory-based interactions, such as navigating through menus [2], entering the boundary of a button,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multitest:Physical-Aware Object Insertion for Testing Multi-Sensor Fusion Perception Systems 24

Multitest:Physical-Aware Object Insertion for Testing Multi-...

引用

44th ACM/IEEE International Conference on software Engineering, ICSE 2024

作者： Gao, Xinyu Wang, Zhijie Feng, Yang Ma, Lei Chen, Zhenyu Xu, Baowen Software Technology Nanjing University State Key Laboratory for Novel China University of Alberta Edmonton Canada The University of Tokyo Japan

ISBN: (纸本)9798400702174

Multi-sensor fusion stands as a pivotal technique in addressing numerous safety-critical tasks and applications, e.g., self-driving cars and automated robotic arms. With the continuous advancement in data-driven artificial intelligence (AI), MSF's potential for sensing and understanding intricate external environments has been further amplified, bringing a profound impact on intelligent systems and specifically on their perception systems. Similar to tra-ditional software, adequate testing is also required for AI-enabled MSF systems. Yet, existing testing methods primarily concentrate on single-sensor perception systems (e.g., image-based and point cloud-based object detection systems). There remains a lack of emphasis on generating multimodal test cases for MSF systems. To address these limitations, we design and implement MULTI-TEST, a fitness-guided metamorphic testing method for complex MSF perception systems. Multitest employs a physical-aware approach to synthesize realistic multimodal object instances and insert them into critical positions of background images and point clouds. A fitness metric is designed to guide and boost the test generation process. We conduct extensive experiments with five SOTA perception systems to evaluate Multitest from the perspectives of: (1) generated test cases' realism, (2) fault detection capabilities, and (3) performance improvement. The results show that Multitest can generate realistic and modality-consistent test data and effectively detect hundreds of diverse faults of an MSF system under test. Moreover, retraining an MSF system on the test cases generated by Multitest can improve the system's robustness. Our replication package and synthesized testing dataset are publicly available at https://***/view/msftest. © 2024 ACM.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Deep Combination of CDCl(T) and Local Search for Satisfiability Modulo Non-Linear Integer Arithmetic Theory 24

Deep Combination of CDCl(T) and Local Search for Satisfiabil...

引用

44th ACM/IEEE International Conference on software Engineering, ICSE 2024

作者： Zhang, Xindi Li, Bohan Cai, Shaowei Institute of Software Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences State Key Laboratory of Computer Science Beijing China

ISBN: (纸本)9798400702174

Satisfiability Modulo Theory (SMT) generalizes the propositional satisfiability problem (SAT) by extending support for various first-order background theories. In this paper, we focus on the SMT problems in Non-Linear Integer Arithmetic (NIA) theory, referred to as SMT(NIA), which has wide applications in software engineering. The dominant paradigm for SMT(NIA) is the CDCL(T) framework, while recently stochastic local search (SLS) has also shown its effectiveness. However, the cooperation between the two methods has not been studied yet. Motivated by the great success of the deep cooperation of CDCL and SLS for SAT, we propose a two-layer hybrid approach for SMT(NIA). The outer-layer interleaves between the inner-layer and an independent SLS solver. In the inner-layer, we take CDCL(T) as the main body, and design DCL(T)-guided SLS solver, which is invoked at branches corresponding to skeleton solutions and returns useful information to improve the branching heuristics of CDCL(T). We implement our ideas on top of the CDCL(T) tactic of Z3 with an SLS solver called Localsmt, resulting in a hybrid solver dubbed Hv-BRIDSMT. Extensive experiments are carried out on the standard SMT(NIA) benchmarks from SMT-LIB, where most of the instances are from real-world software engineering applications of termination and non-termination analysis. Experiment results show that Hybridsmt significantly improves the CDCL(T) solver in Z3. Moreover, our solver can solve 10.36% more instances than the currently best SMT(NIA) solver, and is more efficient for software verification instances. © 2024 ACM.

关键词： Stochastic systems

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：