检索结果-内蒙古大学图书馆

6th International Symposium on computer and Information Processing technology, ISCIPT 2021

作者： Tang, Shun Xiao, Xiaoqiang Li, Baicai Computer School National University of Defense Technology State Key Laboratory of High Performance Computing ChangSha China

ISBN: (纸本)9781665441377

Link prediction is a basic and essential problem in complex network field. There are lots of dynamic networks in reality, nodes and links of which change with time such as online society network, e-commerce network et al. Effective and accurate link prediction for dynamic network is a challenging task because of the potential non-linear characteristics and massive dynamic nature. We propose an end-to-end model named AESAN (Autoencoder Self-Attention Network) that combines autoencoder and self-attention mechanism for dynamic network link prediction task. This model can integrate the structural and temporal evolution features of the dynamic network to achieve high-precision prediction, while effectively reducing the training time. Extensive experiments on real-world dynamic network datasets verified the validity of our model. © 2021 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Making rigorous linear programming practical for program analysis 27

Making rigorous linear programming practical for program ana...

引用

27th International Conference on Principles and Practice of Constraint Programming, CP 2021

作者： Wang, Tengbin Chen, Liqian Chen, Taoqing Fan, Guangsheng Wang, Ji College of Computer National University of Defense Technology Changsha China State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9783959772112

Linear programming is a key technique for analysis and verification of numerical properties in programs, neural networks, etc. In particular, in program analysis based on abstract interpretation, many numerical abstract domains (such as Template Constraint Matrix, constraint-only polyhedra, etc.) are designed on top of linear programming. However, most state-of-the-art linear programming solvers use floating-point arithmetic in their implementations, leading to an approximate result that may be unsound. On the other hand, the solvers implemented using exact arithmetic are too costly. To this end, this paper focuses on advancing rigorous linear programming techniques based on floating-point arithmetic for building sound and efficient program analysis. Particularly, as a supplement to existing techniques, we present a novel rigorous linear programming technique based on Fourier-Mozkin elimination. On this basis, we implement a tool, namely, RlpSolver, combining our technique with existing techniques to lift effectiveness of rigorous linear programming in the scene of analysis and verification. Experimental results show that our technique is complementary to existing techniques, and their combination (RlpSolver) can achieve a better trade-off between cost and precision via heuristic rules. © Tengbin Wang, Liqian Chen, Taoqing Chen, Guangsheng Fan, and Ji Wang.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

A Bayesian validation approach to practical boson sampling

引用

science China(Physics,Mechanics & Astronomy) 2020年第5期63卷 39-46页

作者： Zhe Dai Yong Liu Ping Xu WeiXia Xu XueJun Yang JunJie Wu Institute for Quantum Information&State Key Laboratory of High Performance Computing College of Computer National University of Defense TechnologyChangsha 410073China

Boson sampling is a promising candidate for demonstrating quantum supremacy. The validation that involves judging whether a quantum setup outputs photons following the boson sampling model is an essential task in the experiments. However, the current validation methods may result in an incorrect conclusion being reached in realistic experiments, in which no ideally identical photons exist. Accordingly, this study proposes a slope-based approach, which is an extended Bayesian validation, to model the degree of photon indistinguishability. Through numerical simulations and performance evaluations, we demonstrate that the proposed approach can correctly validate boson sampling against the distribution of classical particles. In addition to offering a useful approach for validation, our research indicates that physicists should pay more attention to the quality of photon indistinguishability in boson sampling experiments.

关键词： boson sampling quantum supremacy Bayesian validation photon indistinguishability

来源：评论

学校读者我要写书评

暂无评论

Hybrid Signal Integrity Modeling and Analysis of Heterogeneous Integrated System With Neuromorphic Darwin Chip

IEEE Transactions on Signal and Power Integrity

引用

IEEE Transactions on Signal and Power Integrity 2024年 3卷 37-46页

作者： Chen, Quankun Ma, Hanzhi Li, Da Tao, Tuomin Tan, Shurun Liu, En-Xiao Schutt-Aine, Jose Li, Er-Ping Zhejiang University Key Laboratory of Advanced Micro/Nano Electronic Devices and Smart Systems and Applications College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang University University of Illinois at Urbana-Champaign Institute Haining314400 China A∗star Institute of High Performance Computing Singapore138632 Singapore University of Illinois at Urbana-Champaign Department of Electrical and Computer Engineering UrbanaIL61820 United States

This article introduces a comprehensive approach for designing and analyzing signal integrity in heterogeneous integrated systems that incorporate neuromorphic Darwin chips. The proposed integrated system architecture includes a neuromorphic Darwin chip, digital signal processing unit, microcontroller unit, field programmable gate arrays, and coding and decoding modules to encode and reconstruct analog spiking signals. The study evaluates the encoding module and the heterogeneous integration structure and conducts signal integrity analysis. To achieve optimal signal integrity performance, the article proposes a novel binocular eye diagram analysis technique. This innovative approach guides the encoding algorithm modification and improves the overall system performance. This research is the first to combine joint field-circuit simulation, heterogeneous integration modeling, and signal integrity analysis of the Darwin neuromorphic chip, and it is expected to serve as a valuable reference for future studies on similar systems. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Seesaw: A 4096 Bits Vector Processor for Accelerating Kyber Based on Risc-V Isa Extensions

SSRN

引用

SSRN 2024年

作者： Zou, Xiaofeng Peng, Yuanxi Li, Tuo Kong, Lingjun Zhang, Lu Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha41003 China Cloud Computing Equipment Industry Innovation Center Jinan250101 China

The Kyber algorithm is one of the standardization of Post Quantum Cryptography project proposed by NIST to withstand quantum attacks. In order to increase throughput and reduce the execution time limited by the high computational complexity of Kyber algorithm, a RISC-V based processor Seesaw is designed to accelerate Kyber algorithm. The 32 specialized extension instructions are firstly designed to enhance the parallel computing ability of the processor and accelerate all processes of the Kyber algorithm by analyzing its characteristic in depth. Then, by carefully designing hardware such as vector registers and algorithm execution units on the RISC-V processor, support of microarchitecture for extension instructions were achieved. Seesaw supports 4096 bits vector calculation through its vector registers and execution unit to meet high-throughput requirements, and is implemented on the FPGA. Besides, we modify the compiler simultaneously to adapt to the instruction extension and execution of Seesaw. Experimental results show that the processor achieves a speed-up of 432× and 18864× for hash and NTT compared to that without extension instructions, respectively, and a speed-up of 5.6× for execution of Kyber algorithm compared with the advanced hardware design. © 2024, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

high-rate discretely-modulated continuous-variable quantum key distribution using quantum machine learning

arXiv

引用

arXiv 2023年

作者： Liao, Qin Liu, Jieyu Huang, Anqi Huang, Lei Fei, Zhuoying Fu, Xiquan College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China

We propose a high-rate scheme for discretely-modulated continuous-variable quantum key distribution (DM CVQKD) using quantum machine learning technologies, which divides the whole CVQKD system into three parts, i.e., the initialization part that is used for training and estimating quantum classifier, the prediction part that is used for generating highly correlated raw keys, and the data-postprocessing part that generates the final secret key string shared by Alice and Bob. To this end, a low-complexity quantum k-nearest neighbor (QkNN) classifier is designed for predicting the lossy discretely-modulated coherent states (DMCSs) at Bob's side. The performance of the proposed QkNN-based CVQKD especially in terms of machine learning metrics and complexity is analyzed, and its theoretical security is proved by using semi-definite program (SDP) method. Numerical simulation shows that the secret key rate of our proposed scheme is explicitly superior to the existing DM CVQKD protocols, and it can be further enhanced with the increase of modulation variance. Copyright © 2023, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

An Efficient Variation-tolerant Method for RRAM-based Neural Network 5

An Efficient Variation-tolerant Method for RRAM-based Neural...

引用

5th IEEE International Conference on Electronics technology, ICET 2022

作者： Huang, Chenglong Xu, Nuo Wang, Junjun Fang, Liang National University of Defense Technology Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Changsha China National University of Defense Technology Institute of Microelectronics and Microprocessors College of Computer Changsha China National Center for Nanoscience and Technology Cas Center for Excellence in Nanoscience Changsha China

ISBN: (纸本)9781665485081

Resistive Random Access Memory (RRAM) is a promising technology for efficient neural computing systems with low power, non-volatile, and good compatibility with CMOS. The RRAM based crossbar is usually employed to accelerate deep neural networks (DNN) because of its intrinsic characteristic of executing multiplication-and-accumulation (MAC) operation according to Kirchhoff's law. However, there are some realistic device issues especially the variation, intrinsic stochastic behavior of RRAM devices, resulting in a significant inference accuracy degradation. In this work, we propose an efficient method that employ the scaling coefficients to improve learning capabilities by providing greater model capacity and compensating for the large information loss due to quantization and device variation. Further, the stochastic noise is added to the weights in training for mimicking device variation to enhance the robustness of DNN to the parameter's variation. We evaluate our method with different mapping methods and initialization conditions of scaling coefficients. Simulation results indicate that our method can rescue the computing accuracy under device variation considering various benchmark datasets(MNIST, Fashion MNIST and CIFAR-10). © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed GAN: Toward a Faster Reinforcement-Learning-Based Architecture Search

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第3期3卷 391-401页

作者： Shi, Jiachen Fan, Yi Zhou, Guoqiang Shen, Jun Nanjing University of Posts and Telecommunications College of Computer Science Nanjing210046 China Nanjing University State Key Laboratory for Novel Software Technology Nanjing210046 China University of Wollongong School of Computing and Information Technology WollongongNSW2522 Australia

In the existing reinforcement learning (RL)-based neural architecture search (NAS) methods for a generative adversarial network (GAN), both the generator and the discriminator architecture are usually treated as the search objects. In this article, we take a different perspective to propose an approach by treating the generator as the search objective and the discriminator as the judge to evaluate the performance of the generator architecture. Consequently, we can convert this NAS problem to a GAN-style problem, similar to using a controller to generate sequential data via reinforcement learning in a sequence GAN, except that the controller in our methods generates serialized data information of architecture. Furthermore, we adopt an RL-based distributed search method to update the controller parameters θ. Generally, the reward value is calculated after the whole architecture searched, but as another novelty in this article, we employ the reward shaping method to judge the intermediate reward and assign it to every cell in the architecture to encourage the diversity and the integrity of all cells. The main contribution of this article is to provide a novel performance estimation mechanism, which could speed up the efficiency of architecture search, and improve the searching results with specific supplementary strategies. Crucially, this estimation mechanism can be applied to most RL-based NAS methods for the GAN. The experiments demonstrate that our methods achieve satisfactory results against our design objectives. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Quantum memory assisted entangled state verification with local measurements

引用

Physical Review Research 2025年第1期7卷 013003-013003页

作者： Siyuan Chen Wei Xie Ping Xu Kun Wang Hefei National Research Center for Physical Sciences at the Microscale and School of Physical Sciences University of Science and Technology of China Hefei 230026 China College of Physics Jilin University Changchun 130012 China School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha 410073 China

We consider the quantum memory assisted quantum state verification task, where an adversary prepares independent multipartite entangled states and sends them to the local verifiers, who then store several copies in the quantum memory and measure them collectively to make a decision. We establish an exact analytic formula for optimizing two-copy state verification, where the verifiers store two copies, and give a globally optimal two-copy strategy for multiqubit graph states involving only Bell measurements. When the verifiers can store arbitrarily many copies, we present a dimension expansion technique that designs efficient verification strategies for this case, showcasing its application to efficiently verifying Greenberger-Horne-Zeilinger (GHZ)-like states. These strategies become increasingly advantageous with growing memory resources, ultimately approaching the theoretical limit of efficiency. Our findings demonstrate that quantum memories enhance state verification efficiency, shedding light on error-resistant strategies and practical applications of large-scale quantum memory assisted verification.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices 38

DapperFL: Domain Adaptive Federated Learning with Model Fusi...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jia, Yongzhe Zhang, Xuyun Hu, Hongsheng Choo, Kim-Kwang Raymond Qi, Lianyong Xu, Xiaolong Beheshti, Amin Dou, Wanchun State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China School of Computing Macquarie University Australia School of Information and Physical Sciences University of Newcastle Australia Department of Information Systems and Cyber Security University of Texas San Antonio United States College of Computer Science and Technology China University of Petroleum [East China China School of Computer and Software Nanjing University of Information Science and Technology China

Federated learning (FL) has emerged as a prominent machine learning paradigm in edge computing environments, enabling edge devices to collaboratively optimize a global model without sharing their private data. However, existing FL frameworks suffer from efficacy deterioration due to the system heterogeneity inherent in edge computing, especially in the presence of domain shifts across local data. In this paper, we propose a heterogeneous FL framework DapperFL, to enhance model performance across multiple domains. In DapperFL, we introduce a dedicated Model Fusion Pruning (MFP) module to produce personalized compact local models for clients to address the system heterogeneity challenges. The MFP module prunes local models with fused knowledge obtained from both local and remaining domains, ensuring robustness to domain shifts. Additionally, we design a Domain Adaptive Regularization (DAR) module to further improve the overall performance of DapperFL. The DAR module employs regularization generated by the pruned model, aiming to learn robust representations across domains. Furthermore, we introduce a specific aggregation algorithm for aggregating heterogeneous local models with tailored architectures and weights. We implement DapperFL on a real-world FL platform with heterogeneous clients. Experimental results on benchmark datasets with multiple domains demonstrate that DapperFL outperforms several state-of-the-art FL frameworks by up to 2.28%, while significantly achieving model volume reductions ranging from 20% to 80%. Our code is available at: https://***/jyzgh/DapperFL. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：