检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Chen, Yaofo Niu, Shuaicheng Wang, Yaowei Xu, Shoukai Song, Hengjie Tan, Mingkui South China University of Technology China Pengcheng Laboratory China Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Pazhou Laboratory China

The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for some period) due to the potential high cost of model adaptation for both the server and edge sides. However, in many real-world scenarios, the test environments may change dynamically (known as distribution shifts), which often results in degraded performance. Thus, one has to adapt the edge models promptly to attain promising performance. Moreover, with the increasing data collected at the edge, this paradigm also fails to further adapt the cloud model for better performance. To address these, we encounter two primary challenges: 1) the edge model has limited computation power and may only support forward propagation;2) the data transmission budget between cloud and edge devices is limited in latency-sensitive scenarios. In this paper, we establish a Cloud-Edge Elastic Model Adaptation (CEMA) paradigm in which the edge models only need to perform forward propagation and the edge models can be adapted online. In our CEMA, to reduce the communication burden, we devise two criteria to exclude unnecessary samples from uploading to the cloud, i.e., dynamic unreliable and low-informative sample exclusion. Based on the uploaded samples, we update and distribute the affine parameters of normalization layers by distilling from the stronger foundation model to the edge model with a sample replay strategy. Extensive experimental results on ImageNet-C and ImageNet-R verify the effectiveness of our CEMA. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Multi-Perspective data Fusion Framework Based on Hierarchical BERT: Provide Visual Predictions of Business Processes

引用

Computers, Materials & Continua 2024年第1期78卷 1227-1252页

作者： Yongwang Yuan Xiangwei Liu Ke Lu School of Mathematics and Big Data Anhui University of Science and TechnologyHuainan232001China School of Economics and Management Anhui University of Science and TechnologyHuainan232001China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji UniversityShanghai201804China

Predictive Business Process Monitoring(PBPM)is a significant research area in Business Process Management(BPM)aimed at accurately forecasting future behavioral *** present,deep learning methods are widely cited in PBPM research,but no method has been effective in fusing data information into the control flow for multi-perspective process ***,this paper proposes a process prediction method based on the hierarchical BERT and multi-perspective data ***,the first layer BERT network learns the correlations between different category attribute ***,the attribute data is integrated into a weighted event-level feature vector and input into the second layer BERT network to learn the impact and priority relationship of each event on future predicted ***,the multi-head attention mechanism within the framework is visualized for analysis,helping to understand the decision-making logic of the framework and providing visual ***,experimental results show that the predictive accuracy of the framework surpasses the current state-of-the-art research methods and significantly enhances the predictive performance of BPM.

关键词： Business process prediction monitoring deep learning attention mechanism BERT multi-perspective

来源：评论

学校读者我要写书评

暂无评论

Application of XGBoost and kernel principal component analysis to forecast oxygen content in ESR

引用

Journal of Iron and Steel Research International 2024年第12期31卷 2940-2952页

作者： Yu-xiao Liu Yan-wu Dong Zhou-hua Jiang Qi Wang Yu-shuo Li School of Metallurgy Northeastern UniversityShenyang110819LiaoningChina National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern UniversityShenyang110819LiaoningChina Key Laboratory of Data Analytics and Optimization for Smart Industry(Northeastern University) Ministry of EducationShenyang110000LiaoningChina Key Laboratory of Ecological Metallurgy of Multimetallic Mineral Northeastern UniversityShenyang110819LiaoningChina

A model combining kernel principal component analysis(KPCA)and Xtreme Gradient Boosting(XGBoost)was introduced for forecasting the final oxygen content of electroslag *** was employed to reduce the dimensionality of the factors influencing the endpoint oxygen content and to eliminate any existing correlations among these *** resulting principal components were then utilized as input variables for the XGBoost prediction *** KPCA-XGBoost model was trained and proven using data obtained from *** model structure was adapted,and hyperparameters were optimized using grid search *** model performance of the KPCA-XGBoost model is compared with five machine learning models,including the support vector regression *** findings demonstrated that the KPCA-XGBoost model exhibited the highest level of prediction accuracy,indicating that the incorporation of KPCA significantly enhanced the regression prediction performance of the *** accuracy of the KPCA-XGBoost model was 82.4%,97.1%,and 100%at errors of±1.5×10^(-6),±2.0×10^(-6),and±3×10^(-6)for oxygen content,respectively.

关键词： Electroslag remelting Oxygen content Machine learning Kernel principal component analysis XGBoost

来源：评论

学校读者我要写书评

暂无评论

High-Dimensional Multi-Label data Stream Classification With Concept Drifting Detection

引用

IEEE Transactions on knowledge and data engineering 2023年第8期35卷 8085-8099页

作者： Li, Peipei Zhang, Haixiang Hu, Xuegang Wu, Xindong Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Second People's Hospital of Hefei Anhui Hefei230011 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education of China School of Computer Science and Information Engineering Anhui Hefei230002 China

Multi-label data streams such as Web texts and images have been popular on the Web. These data present the characteristics of multiple label, high dimensionality, high volume, high velocity and especial concept drift etc. Thus, multi-label data stream classification is a very challenging and significant task especially in the handling of high-dimensional data with concept drifts. However, this challenge has received little attention from the research community. Therefore, we propose the max-relevance and min-redundancy based algorithm adaptation approach for the efficient and effective classification on multi-label data streams with high-dimensional attributes and concept drifts. In order to reduce the impact from the high-dimensional data with noisy attributes, we first refine the minimal-redundancy-maximal-relevance criterion based on mutual information to select qualified features in multi-label data streams. Second, we propose the data distribution based concept drifting detection approach to distinguish concept drifts hidden in data streams. Finally, we build an incremental ensemble classification model for efficiently classifying multi-label data streams. Extensive studies show that our approach can get optimal subsets of features while maintaining a good performance in the multi-label classification, as compared to several state-of-the-art multi-label feature selection algorithms using two efficient multi-label classification methods as base classifiers. Meanwhile, our approach is superior to three well-known multi-label data stream classification approaches in the effectiveness and efficiency. © 1989-2012 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Multi-Cluster Feature Selection Based on Isometric Mapping

引用

IEEE/CAA Journal of Automatica Sinica 2022年第3期9卷 570-572页

作者： Yadi Wang Zefeng Zhang Yinghao Lin Henan Key Laboratory of Big Data Analysis and Processing Henan UniversityKaifeng 475004 Institute of Data and Knowledge Engineering School of Computer and Information EngineeringHenan UniversityKaifeng 475004China

Dear editor,This letter presents an unsupervised feature selection method based on machine *** selection is an important component of artificial intelligence,machine learning,which can effectively solve the curse of d... 详细信息

关键词： problem letter dimensionality

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Semantic Type Identification for Relational Attributes

引用

Journal of Computer Science & Technology 2023年第4期38卷 927-946页

作者：丁玥郭雨荷卢卫李海翔张美慧李晖潘安群杜小勇 Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China Tencent(Beijing)Technology Company Limited Beijing 100080China School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China College of Computer Science and Technology Guizhou UniversityGuiyang 550025China Tencent(Shenzhen)Technology Company Limited Shenzhen 518057China

Identifying semantic types for attributes in relations,known as attribute semantic type(AST)identification,plays an important role in many data analysis tasks,such as data cleaning,schema matching,and keyword search in ***,due to a lack of unified naming standards across prevalent information systems(*** islands),AST identification still remains as an open *** tackle this problem,we propose a context-aware method to figure out the ASTs for relations in this *** transform the AST identification into a multi-class classification problem and propose a schema context aware(SCA)model to learn the representation from a collection of relations associated with attribute values and schema *** on the learned representation,we predict the AST for a given attribute from an underlying relation,wherein the predicted AST is mapped to one of the labeled *** improve the performance for AST identification,especially for the case that the predicted semantic types of attributes are not included in the labeled ASTs,we then introduce knowledge base embeddings(***)to enhance the above representation and construct a schema context aware model with knowledge base enhanced(SCA-KB)to get a stable and robust *** experiments based on real datasets demonstrate that our context-aware method outperforms the state-of-the-art approaches by a large margin,up to 6.14%and 25.17%in terms of macro average F1 score,and up to 0.28%and 9.56%in terms of weighted F1 score over high-quality and low-quality datasets respectively.

关键词： attribute semantic type(AST)identification context-aware semantic embedding knowledge base embedding

来源：评论

学校读者我要写书评

暂无评论

Few-shot 3D Point Cloud Segmentation via Relation Consistency-guided Heterogeneous Prototypes

引用

IEEE Transactions on Multimedia 2025年 27卷 3158-3170页

作者： Wei, Lili Lang, Congyan Xu, Zheming Liang, Liqian Liu, Jun Ministry of Education Key Laboratory of Big Data & Artificial Intelligence in Transportation China Beijing Jiaotong University School of Computer Science & Technology Beijing100044 China Lancaster University LA1 4YW Lancaster United Kingdom

Few-shot 3D point cloud semantic segmentation is a challenging task due to the lack of labeled point clouds (support set). To segment unlabeled query point clouds, existing prototype-based methods learn 3D prototypes from point features of the support set and then measure their distances to the query points. However, such homogeneous 3D prototypes are often of low quality because they overlook the valuable heterogeneous information buried in the support set, such as semantic labels and projected 2D depth maps. To address this issue, in this paper, we propose a novel Relation Consistency-guided Heterogeneous Prototype learning framework (RCHP), which improves prototype quality by integrating heterogeneous information using large multi-modal models (e.g. CLIP). RCHP achieves this through two core components: Heterogeneous Prototype Generation module which collaborates with 3D networks and CLIP to generate heterogeneous prototypes, and Heterogeneous Prototype Fusion module which effectively fuses heterogeneous prototypes to obtain high-quality prototypes. Furthermore, to bridge the gap between heterogeneous prototypes, we introduce a Heterogeneous Relation Consistency loss, which transfers more reliable inter-class relations (i.e., inter-prototype relations) from refined prototypes to heterogeneous ones. Extensive experiments conducted on five point cloud segmentation datasets, including four indoor datasets (S3DIS, ScanNet, SceneNN, NYU Depth V2) and one outdoor dataset (Semantic3D), demonstrate the superiority and generalization capability of our method, outperforming state-of-the-art approaches across all datasets. The code will be released as soon as the paper is accepted. © 1999-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Task Offloading Optimization Based on Position Prediction in Pedestrian- Robot Mixed Traffic Flows 8

Task Offloading Optimization Based on Position Prediction in...

引用

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Zheng, Dawen Wang, Lusheng Kai, Caihong Peng, Min Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9781665450515

Service robots play an increasingly important role in people's daily life. The density of pedestrians is large and the movement is irregular in pedestrian-robot mixed traffic flows. Robots are prone to collision with pedestrians, and the tasks to be offloaded are closely related to pedestrians. How to analyze the tasks of robots and select the appropriate roadside unit is an important issue. In this paper, the social force model is used to predict the positions of pedestrians and robots, taking into account the influence of various forces to avoid collisions. A task offloading resource optimization algorithm with position prediction is proposed. According to the predicted information, the size and position distribution of all tasks in the scenario are obtained, and then the neural network trained beforehand based on deep Q-Iearning is used to generate a task offloading strategy. The simulation results show that the running time of the proposed algorithm is very short, and the resource allocation required for task offloading is completed in advance based on the predicted information before robots arriving the corresponding positions. Besides, the algorithm significantly reduces the task offloading delay. © 2022 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhancing graph representation learning via type-aware decoupling and node influence allocation

引用

Applied Intelligence 2025年第6期55卷 1-14页

作者： Zhu, Guochang Hu, Jun Liu, Li Zhang, Qinghua Wang, Guoyin School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongwen Road Chongqing Chongqing400065 China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongwen Road Chongqing Chongqing400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing400065 China

The traditional graph representation methods can fit the information of graph with low-dimensional vectors, but they cannot interpret their composition, resulting in insufficient security. Graph decoupling, as a method of graph representation, can analyze the latent factors composing the graph representation vectors. However, in current graph decoupling methods, the number of factors is a hyperparameter, and enforce uniform decoupling vector dimensions which leads to information loss or redundancy. To address these issues, we propose a type-aware graph decoupling based on influence called Variational Graph Decoupling Auto-Encoder (VGDAE). It uses node labels as interpretable and objectively existing natural semantics for decoupling and allocates embedding space based on node influence, addressing the issues of manually setting the number of factors in traditional graph decoupling and the mismatch between node information size and embedding space. On the Cora, Citeseer, and fb-CMU datasets, VGDAE shows the impact of different node classes as decoupling targets on classification tasks. Furthermore, we perform visualization of the representations, VGDAE exhibits performance improvements of 2% in classification tasks and 12% in clustering tasks when compared with baseline models. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Short Text Topic Modeling Techniques, Applications, and Performance: A Survey

引用

IEEE Transactions on knowledge and data engineering 2022年第3期34卷 1427-1445页

作者： Qiang, Jipeng Qian, Zhenyu Li, Yun Yuan, Yunhao Wu, Xindong Department of Computer Science Yangzhou University Jiangsu225009 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei Anhui230026 China Mininglamp Academy of Sciences Minininglamp Beijing China

Analyzing short texts infers discriminative and coherent latent topics that is a critical and fundamental task since many real-world applications require semantic understanding of short texts. Traditional long text topic modeling algorithms (e.g., PLSA and LDA) based on word co-occurrences cannot solve this problem very well since only very limited word co-occurrence information is available in short texts. Therefore, short text topic modeling has already attracted much attention from the machine learning research community in recent years, which aims at overcoming the problem of sparseness in short texts. In this survey, we conduct a comprehensive review of various short text topic modeling techniques proposed in the literature. We present three categories of methods based on Dirichlet multinomial mixture, global word co-occurrences, and self-aggregation, with example of representative approaches in each category and analysis of their performance on various tasks. We develop the first comprehensive open-source library, called STTM, for use in Java that integrates all surveyed algorithms within a unified interface, benchmark datasets, to facilitate the expansion of new methods in this research field. Finally, we evaluate these state-of-the-art methods on many real-world datasets and compare their performance against one another and versus long text topic modeling algorithm. © 2020 IEEE.

关键词： Surveys

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：