检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zheng, Muxi Zeng, Jinfeng Yang, Wentao Chang, Pei-Jie Yan, Bao Zhang, Haoran Wang, Min Wei, Shijie Long, Gui-Lu Beijing Academy of Quantum Information Sciences Beijing100193 China State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics Tsinghua University Beijing100084 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore Singapore Frontier Science Center for Quantum Information Beijing100084 China Beijing National Research Center for Information Science and Technology Beijing100084 China

The Learning-With-Errors (LWE) problem is a crucial computational challenge with significant implications for post-quantum cryptography and computational learning theory. Here we propose a quantum-classical hybrid algorithm with Ising model (HAWI) to address the LWE problem. Our approach involves transforming the LWE problem into the Shortest Vector Problem (SVP), using variable qubits to encode lattice vectors into an Ising Hamiltonian. We then identify the low-energy levels of the Hamiltonian to extract the solution, making it suitable for implementation on current noisy intermediate-scale quantum (NISQ) devices. We prove that the number of qubits required is less than m(3m -1)/2, where m is the number of samples in the algorithm. Our algorithm is heuristic, and its time complexity depends on the specific quantum algorithm employed to find the Hamiltonian's low-energy levels. If the Quantum Approximate Optimization Algorithm (QAOA) is used to solve the Ising Hamiltonian problem, and the number of iterations satisfies y © 2024, CC BY-NC-ND.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Efficient Data Valuation Approximation in Federated Learning: A Sampling-based Approach

arXiv

引用

arXiv 2025年

作者： Wei, Shuyue Tong, Yongxin Zhou, Zimu He, Tianran Xu, Yi State Key Laboratory of Complex & Critical Software Environment Lab School of Computer Science and Engineering Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University China City University of Hong Kong Hong Kong

Federated learning (FL) has emerged as a prominent distributed learning paradigm to utilize datasets across multiple data providers. In FL, cross-silo data providers often hesitate to share their high-quality dataset unless their data value can be fairly assessed. Shapley value (SV) has been advocated as the standard metric for data valuation in FL due to its desirable properties. However, the computational overhead of SV is prohibitive in practice, as it inherently requires training and evaluating an FL model across an exponential number of dataset combinations. Furthermore, existing solutions fail to achieve high accuracy and efficiency, making practical use of SV still out of reach, because they ignore choosing suitable computation scheme for approximation framework and overlook the property of utility function in FL. We first propose a unified stratified-sampling framework for two widely-used schemes. Then, we analyze and choose the more promising scheme under the FL linear regression assumption. After that, we identify a phenomenon termed key combinations, where only limited dataset combinations have a high-impact on final data value. Building on these insights, we propose a practical approximation algorithm, IPSS, which strategically selects high-impact dataset combinations rather than evaluating all possible combinations, thus substantially reducing time cost with minor approximation error. Furthermore, we conduct extensive evaluations on the FL benchmark datasets to demonstrate that our proposed algorithm outperforms a series of representative baselines in terms of efficiency and effectiveness. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Adaptive Augmentation for Knowledge Concept Recommendation

Graph Contrastive Learning with Adaptive Augmentation for Kn...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Mei Yu Zhaoyuan Ding Jian Yu Wenbin Zhang Ming Yang Mankun Zhao College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Advanced Networking(TANK Lab) Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Information and Network Center Tianjin University Tianjin China College of Computing and Software Engineering Kennesaw State University Marietta GA USA

Knowledge concept recommendation is a kind of fine-grained recommendation in massive open online courses (MOOCs) scenario, user interaction data has the characteristics of strong collaborative signals and imbalanced interactions. This leads to a single recommendation and reduced accuracy. Recently, the ability of contrastive learning (CL) in mitigating interaction imbalance in recommender systems has received widespread attention. CL requires the use of augmentation methods to generate different views. Existing augmentation methods (1) augment only at the topology or feature level ignoring semantic or structural information, and (2) undifferentiated augmentation tends to lose the critical information. In this paper, we propose Graph Contrastive Learning with Adaptive Augmentation for Knowledge Concept Recommendation (GCARec). Specifically, (1) topology level adaptive augmentation based on degree centrality captures critical structural information, and then (2) feature level adaptive augmentation based on degree centrality captures critical semantic information. Comprehensive experiments show that our proposed approach can outperform other baselines. Our implementations are available at https://***/DingZhaoyuan/GCARec.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combination of Translation and Rotation in Dual Quaternion Space for Temporal Knowledge Graph Completion

Combination of Translation and Rotation in Dual Quaternion S...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ruiguo Yu Tao Liu Jian Yu Wenbin Zhang Yue Zhao Ming Yang Mankun Zhao Jiujiang Guo College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Advanced Networking(TANK Lab) Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Information and Network Center Tianjin University Tianjin China College of Computing and Software Engineering Kennesaw State University Marietta GA USA

Compared with static knowledge graphs (KGs) temporal KGs record the dynamic relations between entities over time, therefore, research on temporal Knowledge Graph Completion (KGC) attracts much attention. Temporal KGs exhibit complex temporal relation patterns, such as multiple relations. However, existing methods can hardly model all the relation patterns and apply to the temporal KGs. In this paper, we propose a novel temporal KGC method that Combining Translation and Rotation (ComTR) in Dual Quaternion Space for temporal KGC. Specifically, we use dual-quaternion-based multiplication to model timestamps and relations as the combination of translation and rotation operations. We analyze the relation patterns of temporal KGs in detail and demonstrate that our method can model all the relation patterns in temporal KGs. Empirically, we show that ComTR can achieve the state-of-the-art performances over four temporal KGC benchmarks datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MASZSL: A Multi-Block Attention-Based Description Generative Adversarial Network for Knowledge Graph Zero-Shot Relational Learning

MASZSL: A Multi-Block Attention-Based Description Generative...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Mei Yu Pengtao Fan Mankun Zhao Wenbin Zhang Yue Zhao Ming Yang Jian Yu College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Advanced Networking(TANK Lab) Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Information and Network Center Tianjin University Tianjin China College of Computing and Software Engineering Kennesaw State University Marietta GA USA

In the real world, the Knowledge Graph(KG) is dynamic and new entities are added at any time. Therefore, open-world Knowledge Graph Completion(KGC) was proposed to approach new-added entities, but previous approaches often introduced too much noise when introducing external text resources for new entities. To alleviate this problem, knowledge graph zero-shot relational learning (KGZSL) has recently attracted more attention. Generative Adversarial Networks (GANs) are frequently used in KGZSL to connect existing relation descriptions to the domain of knowledge graphs. However, these methods ignore the impact of existing entities on embeddings for unidentified relational representations and in-stead concentrate on examining the connection between relational textual texts and knowledge network structures. In this work, we propose a multi-block attention framework using relation Description Generative Adversarial Networks (desGAN) jointing KG and text representation and address model collapse and training stability problems in previous studies. The core idea of our method is to obtain the background knowledge graph information and the relation representation through and multi-block attention layer and the desGAN, then a connection between the structured KG semantic space and the unstructured text semantic space of the new entity is established, forcing the entity pair to be closer to their real relation. Experimental results on the knowledge graph zeroshot relational learning dataset demonstrate that our MASZSL has a faster convergence speed and achieves state-of-the-art performance on this task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mining defects of result-sensitive function based on information entropy 6th

Mining defects of result-sensitive function based on informa...

引用

6th International Conference on Artificial Intelligence and Security,ICAIS 2020

作者： Chen, Lin Yang, Chunfang Liu, Fenlin Gong, Daofu Yin, ZhongXu Zhengzhou Science and Technology Institute Zhengzhou450001 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China

ISBN: (纸本)9789811581007

Result-sensitive function is a typical type of security-sensitive function. The misuse of result-sensitive functions often leads to a lot kinds of software defects. Existing defect detection methods based on code mining for result-sensitive functions usually require a gived security rule or an inferred security rule as input. Based on the principle of consistency, we propose a defect detection method based on information entropy. Firstly, the feature vector about usage of function is extracted from every function instance. Then, the information entropy is introduced to measure the abnormal degree of the feature vector. The function instances with high degree of abnormality is regarded as dangerous instances. Experiments show that the proposed method can effectively detect dangerous instances of security defects without a gived security rule. © Springer Nature Singapore Pte Ltd 2020.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

A Scalable Attention Mechanism Based Neural Network for Text Classification 4

A Scalable Attention Mechanism Based Neural Network for Text...

引用

2019 4th International Seminar on Computer Technology, Mechanical and Electrical engineering, ISCME 2019

作者： Zheng, Jianyun Pang, Jianmin Zhang, Xiaochuan Sun, Di Zhou, Xin Zhang, Kai Wang, Dong Li, Mingliang Wang, Jun State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450002 China Xi'An Institute of Surveying and Mapping Xi'an710000 China

In general, deep learning based text classification methods are considered to be effective but tend to be relatively slow especially for model training. In this work, we present a powerful, so-called "scalable attention mechanism", which performs better than conventional attention mechanism in terms of both effectiveness and the speed of model training. Based on the scalable attention mechanism, we propose a neural network for text classification. The experimental results on eight representative datasets show that our method can obtain similar accuracy to state-of-the-art methods with training in less than 4 minutes on an NVIDIA GTX 1080Ti GPU. To the best of our knowledge, our method is at least twice faster than all the published deep learning classifiers. © 2020 IOP Publishing Ltd. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Modeling of Epitaxial Growth of Single Crystal Superalloys Fabricated by Direct Energy Deposition

SSRN

引用

SSRN 2023年

作者： Shi, Ling Wang, Jiang Xu, Songzhe Li, Jingjing Chen, Chaoyue Hu, Tao Sundar, Hari Ren, Zhongming State Key Laboratory of Advanced Special Steels School of Materials Science and Engineering Shanghai University Shanghai China School of Computing University of Utah Salt Lake City United States

Single crystal (SX) nickel-based superalloys have been used for turbine blades fabrication in recent years because of their superior mechanical performance at high temperature. The restoration of SX blades is significant considering the high cost to re-manufacture the blade. Direct energy deposition (DED), as a laser additive manufacturing technique, is a promising method for repairing the SX blades. Continuous epitaxial growth from the substrate to deposited layers is vital for successful restoration of SX blades. In this work, a novel single crystal texture cellular automata (SITCA) method is developed to simultaneously predict the columnar to equiaxed transition (CET) and crystal growth direction at the molten pool scale. Based on the grain envelope simplification, the SITCA method introduces a random variable to trace the growth trajectory, and therefore indicates the partition of the growth regions in the molten pool. A continuous nucleation model is introduced for nucleation simulation, and the crystal growth is simulated using the KurzGiovanola-Trivedi (KGT) model. The validation of SITCA model is performed by casting solidification cases under uniform temperature and uniform temperature gradient. The SITCA method is then integrated with a thermo-fluid molten pool simulation using finite element method to comprehensively compute the epitaxial growth. SX remelting experiments are carried out with different laser scanning speeds using a flat top laser source, and compared with the numerical results. The experimental and numerical results both indicate that increasing laser scanning speed will increase the ratio of crystals growing in the [001] direction while facilitate the CET on the other hand. This work shows the capacity of the SITCA method to predict epitaxial growth in DED process, and we anticipate to deploy the SITCA method to complex SX additive manufacturing. © 2023, The Authors. All rights reserved.

关键词： Epitaxial growth

来源：评论

学校读者我要写书评

暂无评论

4DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Images

arXiv

引用

arXiv 2024年

作者： Liu, Zhentao Zha, Ruyi Zhao, Huangxuan Li, Hongdong Cui, Zhiming School of Biomedical Engineering State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai China School of Computing Australian National University Canberra Australia School of Computer Science Wuhan University Wuhan China

Reconstructing 3D vessel structures from sparse-view dynamic digital subtraction angiography (DSA) images enables accurate medical assessment while reducing radiation exposure. Existing methods often produce suboptimal results or require excessive computation time. In this work, we propose 4D radiative Gaussian splatting (4DRGS) to achieve high-quality reconstruction efficiently. In detail, we represent the vessels with 4D radiative Gaussian kernels. Each kernel has time-invariant geometry parameters, including position, rotation, and scale, to model static vessel structures. The time-dependent central attenuation of each kernel is predicted from a compact neural network to capture the temporal varying response of contrast agent flow. We splat these Gaussian kernels to synthesize DSA images via X-ray rasterization and optimize the model with real captured ones. The final 3D vessel volume is voxelized from the well-trained kernels. Moreover, we introduce accumulated attenuation pruning and bounded scaling activation to improve reconstruction quality. Extensive experiments on real-world patient data demonstrate that 4DRGS achieves impressive results in 5 minutes training, which is 32× faster than the state-of-the-art method. This underscores the potential of 4DRGS for real-world clinics. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

A Neighbor Immunization Strategy to Block Virus Spreading on Networks

A Neighbor Immunization Strategy to Block Virus Spreading on...

引用

Information Communication Technologies Conference (ICTC)

作者： Hao Yaohui Liu Yingze Zhao Baole Wang Qingxian State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University Zhengzhou China Information Engineering University Zhengzhou China

In order to achieve better effect on blocking virus propagation, a neighbor immunization strategy was proposed and verified in this paper. On email-EU real networks and on scale-free model network, the efficiencies of the neighbor immunization strategy and the random immunization strategy in SIR and SEIR virus spreading models were compared and analyzed by simulation experiment. The result indicates that the neighbor immunization strategy is a feasible and effective. This phenomenon shows that neighbor immunization strategy can improve to the future virus and effectively prevent the virus spreading.

关键词： Analytical models Communications technology Viruses (medical) Immune system

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：