检索结果-内蒙古大学图书馆

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Yu, Hui Zhang, Yu He, Ligang He, Donghao Li, Qikun Zhao, Jin Liao, Xiaofei Jin, Hai Gu, Lin Liu, Haikun National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798400706011

Asynchronous Graph Neural Network (AGNN) has attracted much research attention because it enables faster convergence speed than the synchronous GNN. However, existing software/hardware solutions suffer from redundant computation overhead and excessive off-chip communications for AGNN due to irregular state propagations along the dependency chains between vertices. This paper proposes a chain-driven asynchronous accelerator, CDA-GNN, for efficient AGNN inference. Specifically, CDA-GNN proposes a chain-driven asynchronous execution approach into novel accelerator design to regularize the vertex state propagations for fewer redundant computations and off-chip communications and also designs a chain-aware data caching method to improve data locality for AGNN. We have implemented and evaluated CDA-GNN on a Xilinx Alveo U280 FPGA card. Compared with the cutting-edge software solutions (i.e., Dorylus and AMP) and hardware solutions (i.e., BlockGNN and FlowGNN), CDA-GNN improves the performance of AGNN inference by an average of 1,173x, 182.4x, 10.2x, and 7.9x and saves energy by 2,241x, 242.2x, 12.4x, and 8.9x, respectively. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Evolutionary Reinforcement Learning Algorithm with Early Termination Strategy 23

Adaptive Evolutionary Reinforcement Learning Algorithm with ...

引用

23rd International Conference on Autonomous Agents and Multiagent systems, AAMAS 2024

作者： Wu, Xiaoqiang Zhu, Qingling Lin, Qiuzhen Chen, Weineng Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Computer Science and Engineering South China University of Technology Guangzhou China

Evolutionary reinforcement learning algorithms (ERLs), which combine evolutionary algorithms (EAs) with reinforcement learning (RL), have demonstrated significant success in enhancing RL performance. However, most ERLs rely heavily on Gaussian mutation operators to generate new individuals. When the standard deviation is too large or small, this approach will result in the production of poor or highly similar offspring. Such outcomes can be detrimental to the learning process of the RL agent, as too many poor or similar experiences are generated by these individuals. In order to alleviate these issues, this paper proposes an Adaptive Evolutionary Reinforcement Learning (AERL) method that adaptively adjusts both the standard deviation and the evaluation process. By tracking the performance of new individuals, AERL maintains the mutation strength within a suitable range without the need for additional gradient computations. Moreover, the proposed AERL approach early terminates unnecessary evaluations and discards experiences arising from poor individuals, thereby resulting in enhanced learning efficiency. Empirical assessments conducted on a variety of continuous control problems demonstrate the effectiveness of the AERL method. © 2024 International Foundation for Autonomous Agents and Multiagent systems.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Motif-preserving temporal network embedding 29

Motif-preserving temporal network embedding

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Huang, Hong Fang, Zixuan Wang, Xiao Miao, Youshan Jin, Hai National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory School of Computer Science and Technology Huazhong University of Science and Technology China Beijing University of Posts and Telecommunications China Microsoft Research Asia

ISBN: (纸本)9780999241165

Network embedding, mapping nodes in a network to a low-dimensional space, achieves powerful performance. An increasing number of works focus on static network embedding, however, seldom attention has been paid to temporal network embedding, especially without considering the effect of mesoscopic dynamics when the network evolves. In light of this, we concentrate on a particular motif - triad - and its temporal dynamics, to study the temporal network embedding. Specifically, we propose MTNE, a novel embedding model for temporal networks. MTNE not only integrates the Hawkes process to stimulate the triad evolution process that preserves motif-aware high-order proximities, but also combines attention mechanism to distinguish the importance of different types of triads better. Experiments on various real-world temporal networks demonstrate that, compared with several state-of-the-art methods, our model achieves the best performance in both static and dynamic tasks, including node classification, link prediction, and link recommendation. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

A Fine-Grained Anomaly Detection Method Fusing Isolation Forest and Knowledge Graph Reasoning 19th

A Fine-Grained Anomaly Detection Method Fusing Isolation For...

引用

19th International Conference on Web Information systems and Applications, WISA 2022

作者： Xu, Jie Zhou, Jiantao College of Computer Science Engineering Research Center of Ecological Big Data Ministry of Education National and Local Joint Engineering Research Center of Mongolian Intelligent Information Processing Technology Inner Mongolia Cloud Computing and Service Software Engineering Laboratory Inner Mongolia Social Computing and Data Processing Key Laboratory Inner Mongolia Discipline Inspection and Supervision Big Data Key Laboratory Inner Mongolia Big Data Analysis Technology Engineering Laboratory Inner Mongolia University Hohhot China

ISBN: (纸本)9783031203084

Anomaly detection aims to find outliers data that do not conform to expected behaviors in a specific scenario, which is indispensable and critical in current safety environments related studies. However, when performing outlier detection on a large-scale multidimensional dataset, most of the traditional methods make no distinctions between classes of outliers and lack the reasoning ability and the explainability of the analysis results, which leads to the low accuracy of global outlier detection and the inability to effectively identify local outliers. In this paper, we propose a fine-grained anomaly detection method which well utilizes isolation forest and knowledge graph reasoning tactics. First, a better extracting data feature method and a more reasonable weighted strategy are used to find global outliers based on the traditional isolation forest algorithm, and then we construct a custom rule base according to the in-depth research and analysis of global abnormal data, and at last the ontology knowledge is reasoned based on such rule base to achieve the detection of local outliers. Through analysis of extensive experiment results, our method could effectively discover more abnormal data without big loss of time costs, has strong generalization, and correspondingly improves the performance for abnormal detection. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

ES-Mask: Evolutionary Strip Mask for Explaining Time Series Prediction 37

ES-Mask: Evolutionary Strip Mask for Explaining Time Series ...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Sun, Yifei Song, Cheng Lu, Feng Li, Wei Jin, Hai Zomaya, Albert Y. National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Centre for Distributed and High Performance Computing School of Computer Science University of Sydney Australia

ISBN: (纸本)9781577358800

Machine learning models are increasingly used in time series prediction with promising results. The model explanation of time series prediction falls behind the model development and makes less sense to users in understanding model decisions. This paper proposes ES-Mask, a post-hoc and model-agnostic evolutionary strip mask-based saliency approach for time series applications. ES-Mask designs the mask consisting of strips with the same salient value in consecutive time steps to produce binary and sustained feature importance scores over time for easy understanding and interpretation of time series. ES-Mask uses an evolutionary algorithm to search for the optimal mask by manipulating strips in rounds, thus is agnostic to models by involving no internal model states in the search. The initial experiments on MIMIC-III data set show that ES-Mask outperforms state-of-the-art methods. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model Combined with SVM and CNN for Community Content Classification 23

A Hybrid Model Combined with SVM and CNN for Community Conte...

引用

23rd IEEE International Conference on High Performance computing and Communications, 7th IEEE International Conference on data Science and systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and big data systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Ye, Yukui Xie, Xia Jin, Hai Wang, Duoqiang National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and Technology Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Hainan University Haikou China

ISBN: (纸本)9781665494571

Community websites bring many conveniences to people, and the classification of community content is playing an important role in website management and information searching. As the carrier of community content, posts are difficult to classify manually. According to the characteristics of community content, a hybrid classification model for machine learning is proposed. This model consists of three steps. Firstly, aiming at the problem of fewer features of posts, a weighted word vector is proposed to enrich the features of posts. Secondly, since the single kernel function of SVM can not completely match all data distributions, a mixed kernel function is employed to improve the model. Finally, in order to fully utilize the powerful feature extraction ability of Convolutional Neural Network as well as the classification ability of SVM, a hybrid model is designed and implemented by replacing softmax layer with SVM classifier. The corresponding experiment results indicate that compared with traditional Convolutional Neural Network, the proposed hybrid model has better performance and stability with classification accuracy improved from 0.9% to 1.4% in general. © 2021 IEEE.

关键词： Support vector machines Smart cities Support vector machine classification Machine learning Feature extraction Stability analysis data models

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling of Single-Line Electric Buses with Battery Swapping 8

Optimal Scheduling of Single-Line Electric Buses with Batter...

引用

8th IEEE International Conference on Intelligent Transportation engineering, ICITE 2023

作者： Guo, Yuyan Liu, Tao Institute of System Science and Engineering School of Transportation and Logistics Southwest Jiaotong University National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China

ISBN: (纸本)9798350314212

With the advantages of zero emission and comfortable riding experience, battery-electric buses (BEBs) are widely adopted in public transit agencies as a green alternative to conventional diesel buses. Battery swapping technology is an efficient and promising charging technology to address the issues of battery range anxiety and long battery charging time. This study developed a two-stage optimization model to optimize the single-line battery-electric bus scheduling problem considering battery swapping. At the first stage, a bi-objective integer programming model is established to determine the minimum BEB fleet size, together with the BEB-to-trip assignment and battery swapping schedule. At the second stage, an integer linear programming model is formulated to determine the required minimum number of batteries. An e-constraint method is designed to investigate the trade-off between the required minimum fleet size and the number of back-up batteries. Finally, a real-world case study of a BEB line in Chengdu, China, is conducted to demonstrate the effectiveness of the optimization model and solution method. Sensitivity analyses are further conducted to understand the impacts of some key parameters, including battery capacity, number of trips, cycle time, and battery swapping time. The results show that battery capacity and cycle time have significant influences on BEB-to-trip assignment results and battery swapping schedule. © 2023 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Question generation based on chat-response conversion

Question generation based on chat-response conversion

引用

作者： Zhong, Sheng-Hua Peng, Jianfeng Liu, Peiqi College of Computer Science and Software Engineering Shenzhen University Shenzhen China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Today, thanks to the major breakthrough of sequences to sequences model in the field of natural language, most of the dialogue generation tasks are focused on generating more effective responses. However, the responses proposed by the chat-bot are only a passive answer or assentation, which does not arouse the desire of people to continue communicating. How to transform the chat robot from a passive reply to an active questioner has become an urgent problem. In this paper, a question generalization method with four types of question proposing schemes are designed, implemented, and tested to automate question generation process. The proposed system is controlled by a probability-triggered multiple conversion mechanism to actively propose different types of questions. We embed our methods in the mainstream dialogue generation model and demonstrate its effectiveness in dialogue response generalization on a standard dataset. In addition, it achieves good performance in subjective conversational assessment. © 2019 John Wiley & Sons, Ltd.

关键词： dialogue response generalization system probability-triggered question generation

来源：评论

学校读者我要写书评

暂无评论

Cooperative Relationship Prediction between Scholars in Heterogeneous Academic Network 23

Cooperative Relationship Prediction between Scholars in Hete...

引用

作者： Shi, Jia Jin, Hai Xie, Xia National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and Technology Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Hainan University Haikou China

ISBN: (纸本)9781665494571

The real academic network belongs to a heterogeneous network, therefore, for the link prediction tasks, some information on the network may be lost if only using homogeneous network methods. In order to make good use of the rich semantic information in a heterogeneous network for better predicting the cooperative relationship between scholars, this paper proposes a cooperative relationship prediction (CoRP) model. The CoRP model includes the following three steps. Firstly, a structural feature extraction module is designed based on meta path by using the similarity metric function to measure the meta path similarity between scholars. Secondly, to overcome the defects that the existing methods usually ignore the attribute information on nodes, three attribute feature presentation functions are constructed to fully utilize the attribute information of scholars in the academic network. In the end, a machine learning classifier which combines the structural similarity and attribute similarity is utilized to learn each attribute feature and complete the task of cooperative relationship prediction. The experimental results reveal that compared with the benchmark method, the proposed method has better performance and interpretability with improvement from 3% to 10% of AUC value for the AMiner academic data set. © 2021 IEEE.

关键词： Measurement Smart cities Semantics Machine learning Benchmark testing Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Extended-Isomap for high-dimensional data accuracy and efficiency: a comprehensive survey

引用

Multimedia Tools and Applications 2024年第38期83卷 85523-85574页

作者： Yousaf, Mahwish Shakoor Khan, Muhammad Saadat Ullah, Shamsher Institute of Intelligence Machine Hefei Institutes of Physical Science Chinese Academy of Sciences Anhui Hefei230027 China Key Laboratory of Materials Physics Institute of Solid-State Physics Chinese Academy of Sciences Anhui Hefei230027 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China

Manifold learning is a widely adopted nonlinear dimensionality reduction technique employed to discover low-dimensional representations from high-dimensional data and to explore the intrinsic data structure. It encompasses a range of nonlinear techniques, including Isomap, Local Linear Embedding (LLE), Local Tangent Space Alignment (LTSA), and Multidimensional Scaling (MDS), among others. Isomap, as a popular method in manifold learning, has exhibited promising results. However, it encounters several challenges, such as the Topological Stability Problem, Shortest Path Distance, and noise sensitivity, which compromise its accuracy and elevate its computational demands. This survey paper presents three novel existing approaches to address these challenges and enhance the performance of Isomap. Firstly, the FastIsomap method, an existing approach that combines state-of-the-art algorithms like the KD tree and NN-descent to increase graph accuracy while reducing computational cost. Secondly, the FastIsomapVis method, also an existing technique, employs a hierarchical divide-and-conquer strategy employing the KD tree and Dijkstra Buckets Double, which enhances accuracy and reduces computational time in Isomap. Lastly, the NR-Isomap method, another existing approach, used the Local Tangent Space Alignment algorithm to remove noise sensitivity and short-circuit edge problems. The existing methods improve the accuracy of Isomap but also streamline its computational requirements. Furthermore, this survey paper discusses the open issues and future research directions for Isomap and manifold learning methods. It can be a valuable resource for researchers seeking insights across diverse domains. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Clustering algorithms

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：