检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Kesarwani, Abhishek Insight Centre for Data Analytics School of Computer Science and the Information Technology University of College Cork Ireland

This paper talk about a new method for validating a matrix’s MDS property that outperforms the naive method. The complexity of our method is approximately half that required by the naive approach. The method is also ... 详细信息

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimal Coordination Control For Nonlinear Multi-agent Systems Under Dos Attack

Distributed Optimal Coordination Control For Nonlinear Multi...

引用

第42届中国控制会议

作者： Zhirui Wang Xiaoyuan Zheng Sha Fan School of Artificial Intelligence and Data Science Hebei University of Technology School of Automation East China University of Science and Technology

This paper is concerned with the distributed optimal coordination control of nonlinear multi-agent systems(NMASs)under the denial of service(DoS) attacks. The purpose of this paper is to design a distributed control rate for an unknown nonlinear multi-agent system with power interval and time-varying packet loss probability under Dos attack that accurately simulates the impact of DoS attack on NMASs. Then adaptive dynamic programming(ADP) algorithm is used to solve the coupled Hamilton-Jacobi-Bellman(HJB) equation. In order to realize the proposed method, the critic neural network(NN)and actor neural network are used to approximate value functions and control policy. Finally the NN actor-critic policy for optimal control of NMASs under DoS attack with power interval is found. It is proved that the weight estimation error and local neighborhood coordination error are uniformly ultimately bounded(UUB). Finally, the simulation results show the effectiveness of the coordinated control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative-Contrastive Graph Learning for Recommendation

arXiv

引用

arXiv 2023年

作者： Yang, Yonghui Wu, Zhengwei Wu, Le Zhang, Kun Hong, Richang Zhang, Zhiqiang Zhou, Jun Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China Ant Group China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

By treating users’ interactions as a user-item graph, graph learning models have been widely deployed in Collaborative Filtering (CF) based recommendation. Recently, researchers have introduced Graph Contrastive Learning (GCL) techniques into CF to alleviate the sparse supervision issue, which first constructs contrastive views by data augmentations and then provides self-supervised signals by maximizing the mutual information between contrastive views. Despite the effectiveness, we argue that current GCL-based recommendation models are still limited as current data augmentation techniques, either structure augmentation or feature augmentation. First, structure augmentation randomly dropout nodes or edges, which is easy to destroy the intrinsic nature of the user-item graph. Second, feature augmentation imposes the same scale noise augmentation on each node, which neglects the unique characteristics of nodes on the graph. To tackle the above limitations, we propose a novel Variational Graph Generative-Contrastive Learning (VGCL) framework for recommendation. Specifically, we leverage variational graph reconstruction to estimate a Gaussian distribution of each node, then generate multiple contrastive views through multiple samplings from the estimated distributions, which builds a bridge between generative and contrastive learning. The generated contrastive views can well reconstruct the input graph without information distortion. Besides, the estimated variances are tailored to each node, which regulates the scale of contrastive loss for each node on optimization. Considering the similarity of the estimated distributions, we propose a cluster-aware twofold contrastive learning, a node-level to encourage consistency of a node’s contrastive views and a cluster-level to encourage consistency of nodes in a cluster. Finally, extensive experimental results on three public datasets clearly demonstrate the effectiveness of the proposed model. Copyright © 2023, The Authors.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Optimizing Wireless Coverage and Capacity with PPO-Based Adaptive Antenna Configuration

Optimizing Wireless Coverage and Capacity with PPO-Based Ada...

引用

IEEE International Conference on Communications (ICC)

作者： Yingshuo Gu Shuqi Chai Bowen Sun Yi Chen Qingjiang Shi School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen Research Institute of Big Data China School of Software Engineering Tongji University Shanghai China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Optimizing antenna parameters like azimuth, down-tilt, and power is crucial for coverage and capacity optimization (CCO) in next-generation wireless networks. However, traditional expert knowledge-based methods struggle to maintain optimal results when faced with changing environments. To address this, we propose a guided deep reinforcement learning (DRL) algorithm that learns a policy to dynamically adjust antenna parameters based on the evolving environment. Our approach employs proximal policy optimization-based DRL and integrates a problem-specific pretraining process using zero-order gradient descent. The pretrain policy serves as a guiding policy, enabling the agent to explore and discover high-reward regions, thus accel-erating the learning process. The performance of our solution is validated by numerical experiments conducted on a 5G simulation platform with real-world topological properties. The results show that our approach achieves significantly faster convergence and outperforms baseline methods in terms of CCO performance.

关键词： Heuristic algorithms Wireless networks Neural networks Knowledge based systems Deep reinforcement learning Numerical models Antennas

来源：评论

学校读者我要写书评

暂无评论

Robotic Control Optimization Through Kernel Selection in Safe Bayesian Optimization

Robotic Control Optimization Through Kernel Selection in Saf...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Zheng, Lihao Wang, Hongxuan Li, Xiaocong Ma, Jun Vadakkepat, Prahlad School of Data Science The Chinese University of Hong Kong Research Intern at the Singapore Institute of Manufacturing Technology A∗STAR Shenzhen China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore 138634 Singapore Guangzhou China

ISBN: (纸本)9781665481090

Control system optimization has long been a fundamental challenge in robotics. While recent advancements have led to the development of control algorithms that leverage learning-based approaches, such as SafeOpt, to optimize single feedback controllers, scaling these methods to high-dimensional complex systems with multiple controllers remains an open problem. In this paper, we propose a novel learning-based control optimization method, which enhances the additive Gaussian process-based Safe Bayesian Optimization algorithm to efficiently tackle high-dimensional problems through kernel selection. We use PID controller optimization in drones as a representative example and test the method on Safe Control Gym, a benchmark designed for evaluating safe control techniques. We show that the proposed method provides a more efficient and optimal solution for high-dimensional control optimization problems, demonstrating significant improvements over existing techniques. © 2024 IEEE.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

Boosting Adversarial Robustness Distillation Via Hybrid Decomposed Knowledge

Boosting Adversarial Robustness Distillation Via Hybrid Deco...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yulun Wu Mingrui Lao Yanming Guo Dongmei Chen Tianyuan Yua Laboratory of Big Data and Decision National University of Defense Technology Changsha China Department of Computer Science and Artificial Intelligence University of Granada Granada Spain

Adversarial Robust Distillation (ARD) has emerged as a potent defense mechanism tailored to small models against adversarial threats. However, mainstream ARD methods typically exploit teachers’ response as the transferred knowledge, while neglecting the analysis of involved target-related knowledge to mitigate adversarial attacks. Furthermore, these methods primarily focus on logits-level distillation, which overlook the features-level knowledge in teacher models. In this paper, we introduce a novel Hybrid Decomposed Distillation (HDD) approach, which attempts to identify the vital knowledge against adversarial threats through dual-level distillation. Specifically, we first seek to separate the predictions of teacher model into target-related and target-unrelated knowledge for flexible yet efficient logits-level distillation. Besides, to further boost the distillation efficacy, HDD leverages the channel correlations to decompose intermediate features into highly and less relevant components. Extensive experiments on two benchmarks demonstrate that our HDD achieves superior performance in both clean accuracy and robustness, in contrast to current state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identifying General Mechanism Shifts in Linear Causal Representations 38

Identifying General Mechanism Shifts in Linear Causal Repres...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Tianyu Bello, Kevin Locatello, Francesco Aragam, Bryon Ravikumar, Pradeep Department of Statistics and Data Sciences University of Texas Austin United States Booth School of Business University of Chicago United States Machine Learning Department Carnegie Mellon University United States Institute of Science and Technology Austria Austria

We consider the linear causal representation learning setting where we observe a linear mixing of d unknown latent factors, which follow a linear structural causal model. Recent work has shown that it is possible to recover the latent factors as well as the underlying structural causal model over them, up to permutation and scaling, provided that we have at least d environments, each of which corresponds to perfect interventions on a single latent node (factor). After this powerful result, a key open problem faced by the community has been to relax these conditions: allow for coarser than perfect single-node interventions, and allow for fewer than d of them, since the number of latent factors d could be very large. In this work, we consider precisely such a setting, where we allow a smaller than d number of environments, and also allow for very coarse interventions that can very coarsely change the entire causal graph over the latent factors. On the flip side, we relax what we wish to extract to simply the list of nodes that have shifted between one or more environments. We provide a surprising identifiability result that it is indeed possible, under some very mild standard assumptions, to identify the set of shifted nodes. Our identifiability proof moreover is a constructive one: we explicitly provide necessary and sufficient conditions for a node to be a shifted node, and show that we can check these conditions given observed data. Our algorithm lends itself very naturally to the sample setting where instead of just interventional distributions, we are provided datasets of samples from each of these distributions. We corroborate our results on both synthetic experiments as well as an interesting psychometric dataset. The code can be found at https://***/TianyuCodings/iLCS. © 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

Open Source Software Supply Chain Recommendation Based on Heterogeneous Information Network 14th

Open Source Software Supply Chain Recommendation Based on H...

引用

14th International Symposium on Benchmarking, Measuring, and Optimization, Bench 2022

作者： Lin, HaiMing Liang, Guanyu Wu, Yanjun Wu, Bin Tian, Chunqi Wang, Wei Nanjing Institute of Software Technology Nanjing211135 China School of Computer and Science Tongji University Shanghai201804 China Institude of Software Chinese Academy of Science Beijing100190 China School of Data Science and Engineering East China Normal University Shanghai200062 China

ISBN: (纸本)9783031311796

In the GitHub open-source collaborative development scenario, each entity type and the link relationship between them have natural heterogeneous attributes. In order to improve the accuracy of project recommendation, it is necessary to effectively integrate this multi-source information. Therefore, for the project recommendation scenario, this paper defines an open source weighted heterogeneous information network to represent the different entity types and link relationships in the GitHub open source collaborative development scenario, and effectively model the complex interaction among developers, projects and other entities. Using the weighted heterogeneous information network embedding method, extract and use the rich structural and semantic information in the weighted heterogeneous open source information network to learn the node representation of developers and projects, and fuse the personalized nonlinear fusion function into the matrix decomposition model for open source project recommendation. Finally, this paper makes a large number of comparative experiments based on the real GitHub open data set, and compares it with other project recommendation methods to verify the effectiveness of our proposed open source project recommendation model. At the same time, it also explores the impact of different metapaths on the effect of project recommendation. The experimental results show that the recommendation method based on heterogeneous information network can effectively improve the recommendation quality. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

3H-ObjectDet: A Target Detection Method Based on Haar Wavelet Transform Downsampling and Hybrid Attention Mechanism for Medical Fracture Image 4

3H-ObjectDet: A Target Detection Method Based on Haar Wavele...

引用

4th International Conference on Electronic Information Engineering and Computer Communication, EIECC 2024

作者： Xue, Junmin Rao, Yunbo Yao, Qinwei Wu, Jiangang University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Beijing Youan Hospital Affiliated to Capital Medical University Beijing China Operation Data Center of Postal Savings Bank of China Beijing China

ISBN: (纸本)9798331534622

In recent years, in order to reduce the incidence of misdiagnosis and missed diagnosis in fracture diagnosis and maximize the protection of patients' lives and health, deep learning has achieved rapid development in the field of fracture diagnosis. Target detection models can obtain the location and category of fractures in images simultaneously, and the detection results output are more intuitive, making it convenient for clinical doctors to use directly. However, the following difficulties have troubled clinical use: (1) inefficient extraction of image features, (2) difficulty in accurate detection classification, and (3) large calculation volume causing delayed detection output. This paper proposed a medical fracture image target detection method based on wavelet transform downsampling and mixed attention mechanism, and made relevant innovations: (1) introduced a mixed attention mechanism instead of traditional convolution operation in the feature extraction of the backbone network, (2) innovated the detection classification and localization module to effectively identify features, and (3) simultaneously enhanced feature extraction ability through wavelet transform downsampling and reduced computation. The innovative detection model achieved a 21.2% increase in accuracy and a 10.1% increase in mAP@0.5 in the rib fracture dataset, while reducing computation by 14.8%. In the upper limb fracture and the hand fracture dataset, the high performance indicators have also been significantly increased, showing the high efficiency and generalization of the innovative detection model. © 2024 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Highly Selective Wideband Filtering Stacked DDPA 4

A Highly Selective Wideband Filtering Stacked DDPA

引用

4th IEEE International Conference on Information technology, big data and Artificial Intelligence, ICIBA 2024

作者： Tian, Kang Zhang, JiaSheng La, Dongsheng Northeastern University at Qinhuangdao Hebei Key Laboratory of Marine Perception Network and Data Processing School of Computer and Communication Engineering Qinhuangdao066000 China An Hui Ming Bian Electronic Science & Technology Co. Ltd. China

ISBN: (纸本)9798350363586

In this paper, a compact and highly selective stacked filtering dense dielectric patch (DDP) antenna (DDPA) is proposed. By placing a pair of thin DDP with high dielectric constant along the y axis on the DDP with low dielectric constant, the resonant frequency of the TE12 mode is adjusted to approach low frequency and form a passband with the TE11 mode. By loading a U-shaped microstrip feeding line on the microstrip feeding line, the bandwidth can be further broadened and the TE11, TE11 + δ and TE12 modes can be successfully excited in the passband. The radiation nulls are generated by the U-shaped microstrip line and non-radiative TE12 mode, respectively. By adjusting the length of the U-shaped microstrip line and the size of DDP with high dielectric constant, the independent adjustment of radiation nulls can be achieved. Finally, the proposed filtering antenna achieves a relative bandwidth of 11.66 % (4.04-4.54 GHz). The average realized gain and peak gain are 6.89 dBi and 7.1 dBi, respectively. The realized gain in the passband is very flat, and the fluctuation is less than 0.7 dBi. The proposed antenna has the advantages of compactness, high selectivity and flat gain, and it can be applied to modern satellite communication and wireless communication systems. © 2024 IEEE.

关键词： Bandwidth

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：