检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Yang, Zhiyao Wang, Bing Li, Ximing Wang, Wenting Ouyang, Jihong College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Computer Science University of Texas Dallas United States

Aspect-Based Sentiment Analysis (ABSA) refers to a fine-grained task of detecting the sentiment polarities of sentences at the aspect level. To resolve this task, training samples of ABSA must be annotated with aspect words and the corresponding sentiment polarities. However, collecting such fine-grained training samples is expensive and time consuming. Therefore the available ABSA training samples are often scarce. To break the data scarcity challenge of ABSA, we investigate Semi-supervised Aspect-Based Sentiment Analysis (SemiABSA), which trains ABSA models by using a limited amount of expensive labeled sentences and more unlabeled-yet-cheaper ones. We propose a novel SemiABSA framework, namely Semi-supervised aspect-based Sentiment analysis with Masked aspect prediction (S3MAP), built on the self-training paradigm. For unlabeled sentences, we form pseudo-aspect words and pseudo-sentiment polarities and improve model training. Specifically, a BERT-Encoder-based Masked Aspect Prediction (MAP) task achieves the pseudo-aspect words generation. Based on S3MAP, we thoroughly investigate the potential of SemiABSA from various perspectives. Empirical results show that S3MAP can consistently improve the performance by leveraging unlabeled sentences even with those from different domains. © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Innovative Artificial Intelligence-Based Internet of Things for Smart Cities and Smart Homes

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Sung, Tien-Wen Lee, Chao-Yang Gaber, Tarek Nassar, Hamed Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Taiwan School of Science Engineering & Environment University of Salford Manchester United Kingdom Department of Computer Science Suez Canal University Ismailia Egypt

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Offloading Policies in Multi-Access Edge Computing Systems with Task Handover

arXiv

引用

arXiv 2023年

作者： Hou, Ling Li, Shi Shen, Zhishu Fu, Jing Wu, Jingjin Jin, Jiong School of Engineering STEM College RMIT University Melbourne Australia School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne Australia School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Guangdong Key Laboratory of IRADS Department of Statistics and Data Science BNU-HKBU United International College China

The rapid growth of mobile devices and the increasing complexity of tasks have made energy efficiency a critical challenge in Multi-Access Edge Computing (MEC) systems. This paper explores energy-efficient offloading strategies in large-scale MEC systems with heterogeneous mobile users, diverse network components, and frequent task handovers to capture user mobility. The problem is inherently complex due to the system’s scale, task and resource diversity, and the need to maintain real-time performance. Traditional optimization approaches are often computationally infeasible for such scenarios. To tackle these challenges, we model the offloading problem using the restless multi-armed bandit (RMAB) framework and develop two scalable online policies that prioritize resources based on their marginal costs. The proposed policies dynamically adapt to the system’s heterogeneity and mobility while ensuring near-optimal energy efficiency. Through extensive numerical simulations, we demonstrate that the policies significantly outperform baseline methods in power conservation and show robust performance under non-exponentially distributed task lifespans. These results highlight the practical applicability and scalability of our approach in dynamic MEC *** Codes 93B70 (primary), 68U35 (secondary) Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach for recommending UI element layout

引用

Science China(Information Sciences) 2020年第9期63卷 61-63页

作者： Yonghao LONG Xiangping CHEN Yuting XIE School of Information Science and Technology National Engineering Research Center of Digital LifeSun Yat-sen University Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion School of Communication and Design Sun Yat-sen University

Dear editor,Smartphones and tablets with rich graphical user interfaces (GUI) are becoming increasingly popular. GUI design plays an important role in offering a smooth user experience. The complexity of the apps often depends on the user interface (UI)[1]with minor data processing or data processing delegates to the backend component.

关键词： UI development Software mining Layout recommendation data-driven development Intelligent Software Development

来源：评论

学校读者我要写书评

暂无评论

Cramér-Rao Bound Minimization for IRS-Enabled Multiuser Integrated Sensing and Communications

arXiv

引用

arXiv 2023年

作者： Song, Xianxin Qin, Xiaoqi Xu, Jie Zhang, Rui Shenzhen518172 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

This paper investigates an intelligent reflecting surface (IRS) enabled multiuser integrated sensing and communications (ISAC) system, which consists of one multi-antenna base station (BS), one IRS, multiple single-antenna communication users (CUs), and one target at the non-line-of-sight (NLoS) region of the BS. The IRS is deployed to not only assist the communication from the BS to the CUs, but also enable the BS’s NLoS target sensing based on the echo signals from the BS-IRS-target-IRS-BS link. We consider two types of targets, namely the extended and point targets, for which the BS aims to estimate the complete target response matrix and the target direction-of-arrival (DoA) with respect to the IRS, respectively. To provide full degrees of freedom for sensing, we consider that the BS sends dedicated sensing signals in addition to the communication signals. Accordingly, we model two types of CU receivers, namely Type-I and Type-II CU receivers, which do not have and have the capability of canceling the interference from the sensing signals, respectively. Under each setup, we jointly optimize the transmit beamforming at the BS and the reflective beamforming at the IRS to minimize the Cramér-Rao bound (CRB) for target estimation, subject to the minimum signal-to-interference-plus-noise ratio (SINR) constraints at the CUs and the maximum transmit power constraint at the BS. We present efficient algorithms to solve the highly non-convex SINR-constrained CRB minimization problems, by using the Copyright © 2023, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

RMAvatar: Photorealistic human avatar reconstruction from monocular video based on rectified mesh-embedded Gaussians

引用

Graphical Models 2025年 139卷

作者： Peng, Sen Xie, Weixing Wang, Zilong Guo, Xiaohu Chen, Zhonggui Yang, Baorong Dong, Xiao College of Computer Engineering Jimei University Xiamen China National Institute for Data Science in Health and Medicine Xiamen University Xiamen China Department of Computer Science The University of Texas at Dallas Richardson United States School of Informatics Xiamen University Xiamen China Guangdong Provincial/Zhuhai Key Laboratory of IRADS Beijing Normal-Hong Kong Baptist University Zhuhai China

We introduce RMAvatar, a novel human avatar representation with Gaussian splatting embedded on mesh to learn clothed avatar from a monocular video. We utilize the explicit mesh geometry to represent motion and shape of a virtual human and implicit appearance rendering with Gaussian Splatting. Our method consists of two main modules: Gaussian initialization module and Gaussian rectification module. We embed Gaussians into triangular faces and control their motion through the mesh, which ensures low-frequency motion and surface deformation of the avatar. Due to the limitations of LBS formula, the human skeleton is hard to control complex non-rigid transformations. We then design a pose-related Gaussian rectification module to learn fine-detailed non-rigid deformations, further improving the realism and expressiveness of the avatar. We conduct extensive experiments on public datasets, and RMAvatar shows state-of-the-art performance on both rendering quality and quantitative evaluations. Please see our project page at https://***. © 2025

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Relative manifold based semi-supervised dimensionality reduction

引用

Frontiers of Computer Science 2020年第1期14卷 236-236页

作者： Xianfa CAI Guihua WEN Jia WEI Zhiwen YU School of Medical Information Engineering Guangdong Pharmaceutical UniversityGuangzhou 510006China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China Shenzhen Key Laboratory of High Performance Data Mining Shenzhen 518055China

Figure 8 of this article shows YaleB and CMU PIE with incorrect legend titles:YaleB(Tr=1900,Te=514,NOC=100)should be YaleB(Tr=1900,Te=514,d=100)(Fig.8(a));TIE(Tr=1200,Te=2880,d=100)should be PIE(Tr=1200,Te=2880,d=100)... 详细信息

关键词： Figure dimensionality correct

来源：评论

学校读者我要写书评

暂无评论

Heliostat Relative Efficiency Metric Inspiration for Central Receiver System

SSRN

引用

SSRN 2023年

作者： He, Caitou Chen, Huiling Zhang, Weizhong Zhao, Yuhong Feng, Jieqing College of Computer Science and Artificial Intelligence Wenzhou University Wenzhou325006 China State Key Laboratory of CAD&CG Zhejiang University Hangzhou310058 China Institute of Industrial Intelligence and Systems Engineering College of Control Science and Engineering Zhejiang University Hangzhou310027 China School of Data Science Fudan University Shanghai200433 China

The optimization of heliostat field layout is a topic of considerable interest to both industry and academia, as variations in solar radiation contribution and flux peak at different positions on the site can have significant impacts. Prior research has predominantly focused on optimizing from the perspective of collected solar radiation. Building on the analytical radiative flux distribution model, this study presents a novel relative efficiency metric for heliostat layout optimization, with a focus on peak expression. In this expression, mirror reflectivity, atmospheric attenuation, and receiver cosine effect can all be readily derived from the relative position, whereas the radiation diffusion factor, an important element whose relationship with slant range and slope error is unknown, requires further exploration. To this end, this study undertakes theoretical derivation, experimental simulation, and numerical approximation to determine the relationship between the diffusion factor and slant range for a specific heliostat. Notably, the results of this study demonstrate that the relative efficiency metricis highly consistent with the heliostat layout of PS10, highlighting its potential for practical application. Additionally, the study confirms several heliostat field design logics and principles for central receiver system. © 2023, The Authors. All rights reserved.

关键词： Solar radiation

来源：评论

学校读者我要写书评

暂无评论

Privileged graph distillation for cold start recommendation

arXiv

引用

arXiv 2021年

作者： Wang, Shuai Zhang, Kun Wu, Le Ma, Haiping Hong, Richang Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Anhui University China

The cold start problem in recommender systems is a long-standing challenge, which requires recommending to new users (items) based on attributes without any historical interaction records. In these recommendation systems, warm users (items) have privileged collaborative signals of interaction records compared to cold start users (items), and these Collaborative Filtering (CF) signals are shown to have competing performance for recommendation. Many researchers proposed to learn the correlation between collaborative signal embedding space and the attribute embedding space to improve the cold start recommendation, in which user and item categorical attributes are available in many online platforms. However, the cold start recommendation is still limited by two embedding spaces modeling and simple assumptions of space transformation. As user-item interaction behaviors and user (item) attributes naturally form a heterogeneous graph structure, in this paper, we propose a privileged graph distillation model (PGD). The teacher model is composed of a heterogeneous graph structure for warm users and items with privileged CF links. The student model is composed of an entity-attribute graph without CF links. Specifically, the teacher model can learn better embeddings of each entity by injecting complex higher-order relationships from the constructed heterogeneous graph. The student model can learn the distilled output with privileged CF embeddings from the teacher embeddings. Our proposed model is generally applicable to different cold start scenarios with new user, new item, or new user-new item. Finally, extensive experimental results on the real-world datasets clearly show the effectiveness of our proposed model on different types of cold start problems, with average 6.6%, 5.6%, and 17.1% improvement over state-of-the-art baselines on three datasets, respectively. © 2021, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Train faster, perform better: modular adaptive training in over-parameterized models 23

Train faster, perform better: modular adaptive training in o...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yubin Shi Yixuan Chen Mingzhi Dong Xiaochen Yang Dongsheng Li Yujiang Wang Robert Dick Qin Lv Yingying Zhao Fan Yang Tun Lu Ning Gu Li Shang China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University School of Mathematics Statistics University of Glasgow Microsoft Research Asia Shanghai China Department of Engineering Science University of Oxford Department of Electrical Engineering and Computer Science University of Michigan Department of Computer Science University of Colorado Boulder School of Microelectronics Fudan University

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attain a more efficient and fruitful training strategy. Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue λmax. A large λmax indicates that the module learns features with better convergence, while those miniature ones may impact generalization negatively. Inspired by the discovery, we propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their λmax exceeding a dynamic threshold selectively, concentrating the model on learning common features and ignoring those superfluous ones. Unlike most existing training schemes with a complete BP cycle across all network modules, MAT can significantly save computations by its partially-updating strategy and can further improve performance. Experiments show that MAT nearly halves the computational cost of model training and outperforms the accuracy of baselines.

关键词：

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：