检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Fu, Xingcheng Li, Jianxin Wu, Jia Sun, Qingyun Ji, Cheng Wang, Senzhang Tan, Jiajun Peng, Hao Yu, Philip S. Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Department of Computing Macquarie University Sydney Australia School of Computer Science and Engineering Central South University Changsha410083 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States

Graph Neural Networks (GNNs) have been widely studied in various graph data mining tasks. Most existing GNNs embed graph data into Euclidean space and thus are less effective to capture the ubiquitous hierarchical structures in real-world networks. Hyperbolic Graph Neural Networks (HGNNs) extend GNNs to hyperbolic space and thus are more effective to capture the hierarchical structures of graphs in node representation learning. In hyperbolic geometry, the graph hierarchical structure can be reflected by the curvatures of the hyperbolic space, and different curvatures can model different hierarchical structures of a graph. However, most existing HGNNs manually set the curvature to a fixed value for simplicity, which achieves a suboptimal performance of graph learning due to the complex and diverse hierarchical structures of the graphs. To resolve this problem, we propose an Adaptive Curvature Exploration Hyperbolic Graph Neural Network named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Specifically, ACE-HGNN exploits a multi-agent reinforcement learning framework and contains two agents, ACE-Agent and HGNN-Agent for learning the curvature and node representations, respectively. The two agents are updated by a Nash Q-leaning algorithm collaboratively, seeking the optimal hyperbolic space indexed by the curvature. Extensive experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network

ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Ne...

引用

IEEE International Conference on data Mining (ICDM)

作者： Xingcheng Fu Jianxin Li Jia Wu Qingyun Sun Cheng Ji Senzhang Wang Jiajun Tan Hao Peng Philip S. Yu Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Macquarie University Sydney Australia School of Computer Science and Engineering Central South University Changsha China University of Illinois at Chicago Chicago IL USA

ISBN: (纸本)9781665423991

关键词： Representation learning Geometry Adaptation models Adaptive systems Conferences Reinforcement learning Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust multi-agent differential games for general linear systems with model uncertainties ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 6691-6696页

作者： Fei Liu Xiwang Dong Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Beihang University Beijing 100191 P.R. China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191 P.R. China

The problem of infinite-horizon multi-agent differential games is investigated, where the process can be modeled by a set of uncertain linear dynamics. The players are divided into two teams, one of which consists of a fixed number of follower agents while the other has one leader agent. The two teams constitute the adversaries. The multi-agent differential games can be transformed into a two-player game. The dynamics of the agents are subjected to norm-bound model uncertainties. Based on quadratic stabilization techniques, a set of saddle point strategies of the game is designed to stabilize the closed-loop multi-agent system, where the weighting matrices of the cost function are properly selected. For any given cost function, by modifying the solution of the linear quadratic differential game of the nominal model, the sufficient conditions are presented such that the stabilization of the system is guaranteed and the uncertainties are compensated. It is proved that the modified solution achieves optimality. A numerical example is given to verify the effectiveness of the theoretical results.

关键词： multi-agent system leader-following consensus differential games model uncertainties Nash solution

来源：评论

学校读者我要写书评

暂无评论

Algebraic Analysis of Bifurcations and Chaos for Discrete Dynamical Systems 8th

Algebraic Analysis of Bifurcations and Chaos for Discrete Dy...

引用

8th International Conference on Mathematical Aspects of Computer and Information Sciences, MACIS 2019

作者： Huang, Bo Niu, Wei LMIB-School of Mathematical Sciences Beihang University Beijing100191 China Courant Institute of Mathematical Sciences New York University New York10012 United States Ecole Centrale de Pékin Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

ISBN: (纸本)9783030431198

This paper deals with the stability, bifurcations and chaotic behaviors of discrete dynamical systems by using methods of symbolic computation. We explain how to reduce the problems of analyzing the stability, bifurcations and chaos induced by snapback repellers to algebraic problems, and solve them by using an algorithmic approach based on methods for solving semi-algebraic systems. The feasibility of the symbolic approach is demonstrated by analyses of the dynamical behaviors for several discrete models. © 2020, Springer Nature Switzerland AG.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Integral Sliding-Mode Control of Piecewise Linear systems

Integral Sliding-Mode Control of Piecewise Linear systems

引用

第三十九届中国控制会议

作者： Chunyang Zhang Qing Gao Peng Zhang Kang Zhou School of Automation Science and Eectrical Engineering Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University School of Mechatronical Engineering Beijing Institute of Technology

This paper proposes a dynamic integral sliding-mode control approach for a class of nonlinear systems based on piecewise affine linear models. A general nonlinear system is first modeled equivalently as a uncertain piecewise affine linear system with norm-bounded approximation errors. Based on the equivalent piecewise affine linear system, a dynamic integral sliding-mode control（DISMC） scheme is then proposed. The scheme holds a favorable characteristic in the sense that it allows different input matrices in each subregion, which makes the proposed approach more relaxed than many existing ***, a constructive procedure of the DISMC via convex optimization is presented. Finally, a numerical example is provided to demonstrate the advantages and effectiveness of the developed approach.

关键词： Dynamic integral sliding mode control piecewise affine linear models linear matrix inequality（LMI）

来源：评论

学校读者我要写书评

暂无评论

Wireless Acoustic Sensor Networks and Edge computing for Rapid Acoustic Monitoring

引用

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 64-74页

作者： Zhengguo Sheng Saskia Pfersich Alice Eldridge Jianshan Zhou Daxin Tian Victor C.M.Leung the Department of Engineering and Design University of Sussex Infineon Technologies AG the Department of Music University of Sussex Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems & Safety ControlSchool of Transportation Science and EngineeringBeihang University the Department of Electrical and Computer Engineering The University of British Columbia

Passive acoustic monitoring is emerging as a promising solution to the urgent, global need for new biodiversity assessment methods. The ecological relevance of the soundscape is increasingly recognised, and the affordability of robust hardware for remote audio recording is stimulating international interest in the potential for acoustic methods for biodiversity *** scale of the data involved requires automated methods,however, the development of acoustic sensor networks capable of sampling the soundscape across time and space and relaying the data to an accessible storage location remains a significant technical challenge, with power management at its core. Recording and transmitting large quantities of audio data is power intensive,hampering long-term deployment in remote, off-grid locations of key ecological interest. Rather than transmitting heavy audio data, in this paper, we propose a low-cost and energy efficient wireless acoustic sensor network integrated with edge computing structure for remote acoustic monitoring and in situ *** and computation of acoustic indices are carried out directly on edge devices built from low noise primo condenser microphones and Teensy microcontrollers, using internal FFT hardware support. Resultant indices are transmitted over a ZigBee-based wireless mesh network to a destination *** tests of audio quality, indices computation and power consumption demonstrate acoustic equivalence and significant power savings over current solutions.

关键词： Acoustic sensor networks edge computing energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Dynamical reciprocity in interacting games: Numerical results and mechanism analysis

arXiv

引用

arXiv 2021年

作者： Liang, Rizhou Wang, Qinqin Zhang, Jiqiang Zheng, Guozhong Ma, Lin Chen, Li School of Physics and Information Technology Shaanxi Normal University Xi'an710062 China School of Physics and Electronic-Electrical Engineering Ningxia University Yinchuan750021 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Robert Koch-Institute Nordufer 20 Berlin13353 Germany

We study the evolution of two mutually interacting games with both pairwise games as well as the public goods game on different topologies. On 2d square lattices, we reveal that the game-game interaction can promote the cooperation prevalence in all cases, and the cooperation-defection phase transitions even become absent and fairly high cooperation is expected when the interaction goes to be very strong. A mean-field theory is developed that points out new dynamical routes arising therein. Detailed analysis shows indeed that there are rich categories of interactions in either individual or bulk scenario: invasion, neutral, and catalyzed types;their combination puts cooperators at a persistent advantage position, which boosts the cooperation. The robustness of the revealed reciprocity is strengthened by the studies of model variants, including asymmetrical or time-varying interactions, games of different types, games with time-scale separation, different updating rules etc. The structural complexities of the underlying population, such as Newman-Watts small world networks, Erdos-Rényi random networks, and Barabási-Albert networks, also do not alter the working of the dynamical reciprocity. In particular, as the number of games engaged increases, the cooperation level continuously improves in general. Our work thus uncovers a new class of cooperation mechanism and indicates the great potential for human cooperation where concurrent issues are so often seen in the real world. © 2021, CC BY.

关键词： Mean field theory

来源：评论

学校读者我要写书评

暂无评论

Emergent route towards cooperation in interacting games: The dynamical reciprocity

arXiv

引用

arXiv 2021年

作者： Wang, Qin-Qin Liang, Ri-Zhou Zhang, Ji-Qiang Zheng, Guo-Zhong Ma, Lin Chen, Li School of Physics and Information Technology Shaanxi Normal University Xi'an710062 China School of Physics and Electronic-Electrical Engineering Ningxia University Yinchuan750021 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Robert Koch-Institute Nordufer 20 Berlin13353 Germany

The success of modern civilization is built upon widespread cooperation in human society, deciphering the mechanisms behind has being a major goal for centuries. A crucial fact is, however, largely missing in most prior studies that games in the real world are typically played simultaneously and interactively rather than separately as assumed. Here we introduce the idea of interacting games that different games coevolve and influence each other's decision-making. We show that as the game-game interaction becomes important, the cooperation phase transition dramatically improves, a fairly high level of cooperation is reached for all involved games when interaction goes to be strong. A mean-field theory indicates that a new mechanism - the dynamical reciprocity, as a counterpart to the well-known network reciprocity, is at work to foster cooperation, which is confirmed by the detailed analysis. This revealed reciprocity is robust against variations in the game type, the population structure, and the updating rules etc, and more games generally yield a higher level of cooperation. Our findings point out the great potential towards high cooperation for many issues are interwoven with each other in the real world, and also the possibility of sustaining decent cooperation even in extremely adverse circumstances. © 2021, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Codebleu: a method for automatic evaluation of code synthesis

arXiv

引用

arXiv 2020年

作者： Ren, Shuo Guo, Daya Lu, Shuai Zhou, Long Liu, Shujie Tang, Duyu Sundaresan, Neel Zhou, Ming Blanco, Ambrosio Ma, Shuai SKLSDE Lab Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing China Sun Yat-sen University China Peking University China Microsoft United States

Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models. In the area of code synthesis, the commonly used evaluation metric is BLEU or perfect accuracy, but they are not suitable enough to evaluate codes, because BLEU is originally designed to evaluate natural language, neglecting important syntactic and semantic features of codes, and perfect accuracy is too strict thus it underestimates different outputs with the same semantic logic. To remedy this, we introduce a new automatic evaluation metric, dubbed CodeBLEU. It absorbs the strength of BLEU in the n-gram match, and further injects code syntax via abstract syntax trees (AST) and code semantics via data-flow. We conduct experiments by evaluating the correlation coefficient between CodeBLEU and quality scores assigned by the programmers on three code synthesis tasks, i.e., text-to-code, code translation, and code refinement. Experimental results show that, our proposed CodeBLEU can achieve a better correlation with programmer assigned scores compared with BLEU and accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Nonreciprocal coherent coupling of nanomagnets by exchange spin waves

引用

Nano Research 2021年第7期14卷 2133-2138页

作者： Hanchen Wang Jilei Chen Tao Yu Chuanpu Liu Chenyang Guo Song Liu Ka Shen Hao Jia Tao Liu Jianyu Zhang Marco A.Cabero Z Qiuming Song Sa Tu Mingzhong Wu Xiufeng Han Ke Xia Dapeng Yu Gerrit E.W.Bauer Haiming Yu Fert Beijing Institute School of Integrated Circuit Science and EngineeringBeijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China Max Planck Institute for the Structure and Dynamics of Matter 22761 HamburgGermany Beijing National Laboratory for Condensed Matter Physics Institute of PhysicsUniversity of Chinese Academy of SciencesChinese Academy of SciencesBeijing 100190China Shenzhen Institute for Quantum Science and Engineering(SIQSE) and Department of PhysicsSouthern University of Science and Technology(SUSTech)Shenzhen 518055China Department of Physics Beijing Normal UniversityBeijing 100875China Department of Physics Colorado State UniversityFort CollinsColorado 80523USA Kavli Institute of Nanoscience Delft University of Technology2628 CJ DelftThe Netherlands Institute for Materials Research WPI-AIMR and CSNRTohoku UniversitySendai 980-8577Japan Zernike Institute for Advanced Materials University of GroningenGroningenNijenborgh 49747 AG GroningenThe Netherlands

Nanomagnets are widely used to store information in non-volatile spintronic *** waves can transfer information with low-power consumption as their propagations are independent of charge ***,to dynamically couple two distant nanomagnets via spin waves remains a major challenge for *** we experimentally demonstrate coherent coupling of two distant Co nanowires by fast propagating spin waves in an yttrium iron garnet thin film with sub-50 nm *** in two nanomagnets are unidirectionally phase-locked with phase shifts controlled by magnon spin torque and spin-wave *** coupled system is finally formulated by an analytical theory in terms of an effective non-Hermitian *** results are attractive for analog neuromorphic computing that requires unidirectional information transmission.

关键词： spintronics nanomagnets spin waves coherent coupling nonreciprocity

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：