检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Synthesizing Barrier Certificates of Neural Network Controlled Continuous Systems via Approximations 21

Synthesizing Barrier Certificates of Neural Network Controll...

引用

Proceedings of the 58th Annual ACM/IEEE Design Automation Conference

作者： Meng Sha Xin Chen Yuzhe Ji Qingye Zhao Zhengfeng Yang Wang Lin Enyi Tang Qiguang Chen Xuandong Li State Key Laboratory for Novel Software Technology of Nanjing University Nanjing China Shanghai Key Lab of Trustworthy Computing of East China Normal University Shanghai China School of Information Science and Technology of Zhejiang Sci-Tech University Hangzhou China British Columbia Academy Nanjing China

ISBN: (纸本)9781665432740

The paper presents a barrier certificate based approach to verifying safety properties of closed-loop systems using neural networks as controllers. It deals with the verification problem in the infinite time horizon and exploits the approximated system of the original one to synthesize the candidate barrier certificates, where the behavior of a neural network controller is approximated by a polynomial with a bounded error. Satisfiability Modulo Theories solvers are then utilized to identify real barrier certificates from those candidates. As a barrier certificate can separate the over-approximation of the reachable set from the unsafe region, once it is constructed, the safety property gets proved. We show the advantage of our approach in barrier certificates synthesis by comparing it with the state-of-the-art work on a set of benchmarks.

关键词： safety verification

来源：评论

学校读者我要写书评

暂无评论

novel approach of the best path selection based on prior knowledge reinforcement learning 3

Novel approach of the best path selection based on prior kno...

引用

3rd IEEE International Conference on Smart Internet of Things, SmartIoT 2019

作者： Liu, Xiao-Huan Zhang, De-Gan Zhang, Ting Cui, Yu-Ya Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9781728134888

This paper proposes and designs a novel approach to solve the optimal path planning problem of intelligent driving vehicles in practical applications. Through the understanding and learning of the reinforcement learning algorithm, we proposed a novel approach of the best path selection with length priority based on the prior knowledge applied reinforcement learning strategy, and improved the search direction setting of the shortest path in the program, simplified the process of shortest path search. This path optimization method can effectively help different types of intelligent driving vehicles to smoothly select the best path in the traffic network with limited height, width and weight, accident and traffic jam. Through simulation experiments and scene experiments, it is proved that the proposed algorithm has good stability, high efficiency and practicability. © 2019 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Representation Learning Framework for Stock Movement Prediction

SSRN

引用

SSRN 2022年

作者： Feng, Wenzhi Ma, Xiang Li, Xuemei Zhang, Caiming School of Software Shandong University Jinan250101 China Shandong Co-Innovation Center of Future Intelligent Computing Yantai264025 China Digital Media Technology Key Lab of Shandong Province Jinan250014 China

The learning of high-quality stock representations is one of the keys to predicting stock movements effectively. Current studies have been negatively impacted by stochasticity in stock prices, resulting in inadequate representation learnt by the models. We present an end-to-end stock movement prediction framework (CLSR) utilizing contrastive learning to exploit the correlation between intra-day data and enhance stock representation in order to improve the accuracy of stock movement prediction. In addition, a hybrid encoding network is developed to extract long-range dependencies and local contextual features in stock data, making the feature representation more complete. To further improve the prediction accuracy of the model, historical state information is added to the intra-day stock data. Our experiments on CSI-500 show that the proposed method outperforms state-of-the-art solutions. The proposed method is also validated by analyzing the representation space thoroughly © 2022, The Authors. All rights reserved.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

An Effective Network Repair Strategy Against Both Random and Malicious Edge Attacks

An Effective Network Repair Strategy Against Both Random and...

引用

第40届中国控制会议

作者： Jianda Zhao Shiwen Sun Hao Shen Chengyi Xia School of Computer Science and Engineering Tianjin University of Technology Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education

Attack vulnerability and protection of large-scale complex networks are of great significance in academic and engineering *** this study,the problem of structural vulnerability of complex networks induced by attacks on edges is *** order to restore network’s performance after attacks,a simple two-stage attack-recovery model based on activating backup edges is ***,with the consideration of two different edge attack strategies,the joint influence of repair cost（*** extent of edge redundancy） and repair targets are extensively *** simulations are implemented on artificially generated random networks and real-world networks,which demonstrate the effectiveness of proposed repair *** research results can provide some useful suggestion on constructing robust infrastructure systems,also help to better understand the structural complexity of large-scale networks.

关键词： Complex network attack structural vulnerability repair cost redundant edges

来源：评论

学校读者我要写书评

暂无评论

Online Attentive Kernel-Based Temporal Difference Learning

arXiv

引用

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Algebraic analysis and control of networked opacity with bounded communication delays

Algebraic analysis and control of networked opacity with bou...

引用

第40届中国控制会议

作者： Qian Xu Zhipeng Zhang Chengyi Xia Zengqiang Chen Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education College of Artificial Intelligence Nankai University

Networked finite state machine takes the delay factor into consideration, and its security has become an significant research topic. In this paper, we explore the impact of bounded communication delays on networked opacity of finite state machine from an algebraic point. Firstly, by making use of Boolean semi-tensor product（Boolean STP）, we propose an algebraic equation to characterize the current dynamics with bounded observation delays. Subsequently, we give the verification criterion for networked opacity, and calculate the delayed dynamics by introducing the state reachability matrix. Meanwhile, we investigate the effect of bound number on the opacity-enforcement problem, and compute the minimum bound of communication delay to ensure the state opacity property. Finally, a numerical example is provided to demonstrate the results.

关键词： Semi-tensor product（STP） of matrices finite state machine state opacity observation delays

来源：评论

学校读者我要写书评

暂无评论

A Many-Objective Evolutionary Algorithm Assisted by Ideal Hyperplane

SSRN

引用

SSRN 2022年

作者： Zhang, Zhixia Wen, Jie Wang, Hui Cai, Xingjuan Cui, Zhihua Zhang, Wensheng School of Computer Science and Technology Taiyuan University of Science and Technology China School of Information Engineering Nanchang Institute of Technology Nanchang330099 China State Key Laboratory of Intelligent Control and Management of Complex System Institute of Automation Chinese Academy of Sciences China State Key Lab. for Novel Software Technology Nanjing University China

In many-objective optimization problems (MaOPs), it is a difficult task for evolutionary algorithms to balance convergence and diversity while rapidly converging to the Pareto front. As the number of objectives increases, the difficulty of evolutionary algorithms increases with individual selection pressure. To address above problems, we propose a many-objective evolution algorithm assisted by an ideal hyperplane (MaOEA-IH). Firstly, the ideal hyperplane as a reference surface to guide the individual to search the Pareto front, which is established from the extremum of each dimension of the objective space. Secondly, a parallel p -norm mating selection strategy is proposed to improve convergence. In addition, two factors are considered in this strategy: 1) different p -norm are used to measure different spatial scales;2) individual selection uncertainty is defined by incorporating a probabilistic perturbation mechanism. Thirdly, the improved shift-based density estimation strategy is used as the evaluation criterion for environmental selection to improve the convergence and diversity of solution sets and enhance selection pressure. To verify the effectiveness of the proposed algorithm, MAOEA-IH is compared with seven excellent algorithms in three benchmark sets (DTLZ, WFG and MaF). The results show that the proposed MAOEA-IH is highly competitive in solving MaOPs. © 2022, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Xiao, Zhiqing Wang, Haobo Jin, Ying Feng, Lei Chen, Gang Huang, Fei Zhao, Junbo College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University China CUHK-SenseTime Joint Lab The Chinese University of Hong Kong Hong Kong School of Computer Science and Engineering Nanyang Technological University Singapore Alibaba Group China

Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the in-domain model to the distinctive target domains where the data distributions differ. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff. The core of our method is briefly condensed as follows: (i)-by casting the DA problem to graph primitives, SPA composes a coarse graph alignment mechanism with a novel spectral regularizer towards aligning the domain graphs in eigenspaces;(ii)-we further develop a fine-grained message propagation module — upon a novel neighbor-aware self-training mechanism — in order for enhanced discriminability in the target domain. On standardized benchmarks, the extensive experiments of SPA demonstrate that its performance has surpassed the existing cutting-edge DA methods. Coupled with dense model analysis, we conclude that our approach indeed possesses superior efficacy, robustness, discriminability, and transferability. Code and data are available at: https://***/CrownX/SPA. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval

arXiv

引用

arXiv 2022年

作者： Shen, Yang Sun, Xuhao Wei, Xiu-Shen Jiang, Qing-Yuan Yang, Jian School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Integrated Services Networks Xidian University China State Key Laboratory for Novel Software Technology Nanjing University China Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing University of Science and Technology China

In this paper, we propose Suppression-Enhancing Mask based attention and Interactive Channel transformatiON (SEMICON) to learn binary hash codes for dealing with large-scale fine-grained image retrieval tasks. In SEMICON, we first develop a suppression-enhancing mask (SEM) based attention to dynamically localize discriminative image regions. More importantly, different from existing attention mechanism simply erasing previous discriminative regions, our SEM is developed to restrain such regions and then discover other complementary regions by considering the relation between activated regions in a stage-by-stage fashion. In each stage, the interactive channel transformation (ICON) module is afterwards designed to exploit correlations across channels of attended activation tensors. Since channels could generally correspond to the parts of fine-grained objects, the part correlation can be also modeled accordingly, which further improves fine-grained retrieval accuracy. Moreover, to be computational economy, ICON is realized by an efficient two-step process. Finally, the hash learning of our SEMICON consists of both global- and local-level branches for better representing fine-grained objects and then generating binary hash codes explicitly corresponding to multiple levels. Experiments on five benchmark fine-grained datasets show our superiority over competing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Image retrieval

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：