检索结果-内蒙古大学图书馆

Heterogeneous-attributes enhancement deep framework for network embedding

Frontiers of Computer Science 2021年第6期15卷 121-131页

作者： Lisheng QIAO Fan ZHANG Xiaohui HUANG Kai LI Enhong CHEN Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230022China National Key Laboratory of Blind Signal Processing Chengdu 610041China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230022China

Network embedding,which targets at learning the vector representation of vertices,has become a crucial issue in network ***,considering the complex structures and heterogeneous attributes in real-world networks,existing methods may fail to handle the inconsistencies between the structure topology and attribute ***,more comprehensive techniques are urgently required to capture the highly non-linear network structure and solve the existing inconsistencies with retaining more *** that end,in this paper,we propose a heterogeneous-attributes enhancement deep framework(HEDF),which could better capture the non-linear structure and associated information in a deep learningway,and effectively combine the structure information of multi-views by the combining *** this line,the inconsistencies will be handled to some extent and more structure information will be preserved through a semi-supervised *** extensive validations on several real-world datasets show that our model could outperform the baselines,especially for the sparse and inconsistent situation with less training data.

关键词： network embedding heterogeneous-attributes deep framework inconsistent

来源：评论

学校读者我要写书评

暂无评论

Adam revisited:a weighted past gradients perspective

引用

Frontiers of Computer Science 2020年第5期14卷 61-76页

作者： Hui Zhong Zaiyi Chen Chuan Qin Zai Huang Vincent W.Zheng Tong Xu Enhong Chen Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei230027China Zhejiang Cainiao Supply Chain Management Co.Ltd Hangzhou311122China Advanced Digital Sciences Center Singapore138602Singapore

Adaptive learning rate methods have been successfully applied in many fields,especially in training deep neural *** results have shown that adaptive methods with exponential increasing weights on squared past gradients(i.e.,ADAM,RMSPROP)may fail to converge to the optimal *** many algorithms,such as AMSGRAD and ADAMNC,have been proposed to fix the non-convergence issues,achieving a data-dependent regret bound similar to or better than ADAGRAD is still a challenge to these *** this paper,we propose a novel adaptive method weighted adaptive algorithm(WADA)to tackle the non-convergence *** AMSGRAD and ADAMNC,we consider using a milder growing weighting strategy on squared past gradient,in which weights grow *** on this idea,we propose weighted adaptive gradient method framework(WAGMF)and implement WADA algorithm on this ***,we prove that WADA can achieve a weighted data-dependent regret bound,which could be better than the original regret bound of ADAGRAD when the gradients decrease *** bound may partially explain the good performance of ADAM in ***,extensive experiments demonstrate the effectiveness of WADA and its variants in comparison with several variants of ADAM on training convex problems and deep neural networks.

关键词： adaptive learning rate methods stochastic gradient descent online learning

来源：评论

学校读者我要写书评

暂无评论

Illuminating Recommendation by Understanding the Explicit Item Relations

引用

Journal of Computer Science & Technology 2018年第4期33卷 739-755页

作者： Qi Liu Hong-Ke Zhao Le Wu Zhi Li En-Hong Chen Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Hefei 230027 China School of Computer and Information Hefei University of Technology Hefei 230009 China School of Software Engineering University of Science and Technology of China Hefei 230051 China

Recent years have witnessed the prevalence of recommender systems in various fields, which provide a personalized recommendation list for each user based on various kinds of information. For quite a long time, most researchers have been pursing recommendation performances with predefined metrics, e.g., accuracy. However, in real-world applications, users select items from a huge item list by considering their internal personalized demand and external constraints. Thus, we argue that explicitly modeling the complex relations among items under domain-specific applications is an indispensable part for enhancing the recommendations. Actually, in this area, researchers have done some work to understand the item relations gradually from ＂implicit＂ to ＂explicit＂ views when recommending. To this end, in this paper, we conduct a survey of these recent advances on recommender systems from the perspective of the explicit item relation understanding. We organize these relevant studies from three types of item relations, i.e., combination-effect relations, sequence-dependence relations, and external-constraint relations. Specifically, the combination-effect relation and the sequence-dependence relation based work models the intra-group intrinsic relations of items from the user demand perspective, and the external-constraint relation emphasizes the external requirements for items. After that, we also propose our opinions on the open issues along the line of understanding item relations and suggest some future research directions in recommendation area.

关键词： recommender system item relation recommendation interpretability

来源：评论

学校读者我要写书评

暂无评论

Accelerating local SGD for non-IID data using variance reduction

引用

Frontiers of Computer Science 2023年第2期17卷 73-89页

作者： Xianfeng LIANG Shuheng SHEN Enhong CHEN Jinchang LIU Qi LIU Yifei CHENG Zhen PAN Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230027China Ant Financial Services Group Hangzhou 310000China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China

Distributed stochastic gradient descent and its variants have been widely adopted in the training of machine learning models,which apply multiple workers in *** them,local-based algorithms,including Local SGD and FedAvg,have gained much attention due to their superior properties,such as low communication cost and ***,when the data distribution on workers is non-identical,local-based algorithms would encounter a significant degradation in the convergence *** this paper,we propose Variance Reduced Local SGD(VRL-SGD)to deal with the heterogeneous *** extra communication cost,VRL-SGD can reduce the gradient variance among workers caused by the heterogeneous data,and thus it prevents local-based algorithms from slow convergence ***,we present VRL-SGD-W with an effectivewarm-up mechanism for the scenarios,where the data among workers are quite *** from eliminating the impact of such heterogeneous data,we theoretically prove that VRL-SGD achieves a linear iteration speedup with lower communication complexity even if workers access non-identical *** conduct experiments on three machine learning *** experimental results demonstrate that VRL-SGD performs impressively better than Local SGD for the heterogeneous data and VRL-SGD-W is much robust under high data variance among workers.

关键词： distributed optimization variance reduction local SGD federated learning non-IID data

来源：评论

学校读者我要写书评

暂无评论

Legal Judgment Prediction with Multiple Perspectives on Civil Cases 1st

Legal Judgment Prediction with Multiple Perspectives on Civi...

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Zhao, Lili Yue, Linan An, Yanqing Liu, Ye Zhang, Kai He, Weidong Chen, Yanmin Yuan, Senchao Liu, Qi Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science and School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9783030930455

Legal Judgment Prediction, which aims at predicting the judgment result based on case materials, is an essential task in Legal Intelligence. Most existing studies have analyzed and modeled criminal cases as a whole, while a small part of the research focuses on civil cases which are also significant in the legal system. In these studies, most model on a certain type of civil causes and make the judgment prediction based on the ascertained fact from the perspective of the court. However, in real-world scenarios, there are different civil cases on various causes, and every case is judged from multiple perspectives (i.e., plaintiff, defendant, and the court). It is difficult to make judgment predictions on various civil causes. To address the above challenges, in this paper, we propose a novel Civil Case Judgment (CCJudge) prediction method by simulating the logic of judges. Following this logic, we construct an external knowledge base that contains the explanations and applications of every cause, it helps make the judgment on various causes. Furthermore, a special encoder layer and interaction layer are designed for learning linguistic semantics from multiple perspectives. We conduct extensive experiments on a real-world dataset. The experimental results demonstrate the effectiveness of our method. © 2021, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Correction: FragGen: towards 3D geometry reliable fragment-based molecular generation

引用

Chemical science 2025年第3期16卷 1467页

作者： Odin Zhang Yufei Huang Shicheng Chen Mengyao Yu Xujun Zhang Haitao Lin Yundian Zeng Mingyang Wang Zhenxing Wu Huifeng Zhao Zaixi Zhang Chenqing Hua Yu Kang Sunliang Cui Peichen Pan Chang-Yu Hsieh Tingjun Hou College of Pharmaceutical Sciences Zhejiang University Hangzhou 310058 Zhejiang China slcui@*** panpeichen@*** kimhsieh@*** tingjunhou@***. Zhejiang University Hangzhou 310058 Zhejiang China. Anhui Province Key Lab of Big Data Analysis and Application University of Science and Technology of China Hefei Anhui China. Montreal Institute for Learning Algorithms McGill University Montreal QC Canada.

[This corrects the article DOI: 10.1039/D4SC04620J.].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Semantic Matching with Self Attention Mechanism 5

Context-Aware Semantic Matching with Self Attention Mechanis...

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Chen, Yanmin Wang, Hao Sun, Ruijun Chen, Enhong University of Science and Technology of China The Anhui Province Key Laboratory of Big Data Analysis and Application Hefei China Xinjiang Normal University Hefei China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

As we know, semantic matching plays a very important role in the field of natural language processing, and is the basis of many other language applications, such as question answer matching, chat robots and customer service. Though large efforts have been made, they mainly focus on the semantic matching of a single sentence pair. However, in many real-world scenarios, a sentence tends to have semantic associations with multiple sentences. So these relational information between sentences has been largely ignored in previous research work. To this end, in this paper, we propose a novel Self-attention Relational Sentence Semantic Matching (SR-SSM) framework in order to jointly utilize the sentences and relational information to achieve better semantic matching. Specifically, we first utilize the LSTM network to obtain the original sentence representation. Then we incorporate the information of adjacent sentences to obtain context-aware sentence representation through the self-attention mechanism. Finally, we adopt a multi-layer perceptron to model interactions between sentence pairs and predict the semantic similarity. Experiments on public datasets have validated the effectiveness of SR-SSM with a significant margin compared with the state-of-the-art baselines. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Leveraging proficiency and preference for online Karaoke recommendation

引用

Frontiers of Computer Science 2020年第2期14卷 273-290页

作者： Ming HE Hao GUO Guangyi LV Le WU Yong GE Enhong CHEN Haiping MA Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230027China School of Computer and Information Hefei University of TechnologyHefei 230026China Eller College of Management The University of ArizonaArizona 85721-0108USA iFlyTek Research Hefei 230026China

Recently,many online Karaoke(KTV)platforms have been released,where music lovers sing songs on these *** the meantime,the system automatically evaluates user proficiency according to their singing *** approximate songs to users can initialize singers5 participation and improve users,loyalty to these ***,this is not an easy task due to the unique characteristics of these ***,since users may be not achieving high scores evaluated by the system on their favorite songs,how to balance user preferences with user proficiency on singing for song recommendation is still ***,the sparsity of the user-song interaction behavior may greatly impact the recommendation *** solve the above two challenges,in this paper,we propose an informationfused song recommendation model by considering the unique characteristics of the singing ***,we first devise a pseudo-rating matrix by combing users’singing behavior and the system evaluations,thus users'preferences and proficiency are *** we mitigate the data sparsity problem by fusing users*and songs'rich information in the matrix factorization process of the pseudo-rating ***,extensive experimental results on a real-world dataset show the effectiveness of our proposed model.

关键词： KTV matrix factorization recommendation system

来源：评论

学校读者我要写书评

暂无评论

Traffic optimization method at five-way intersection based on green building materials and signal processing

Traffic optimization method at five-way intersection based o...

引用

2022 International Conference on Signal Processing and Communication Security, ICSPCS 2022

作者： Liang, Zijun Zhan, Xuejuan Kong, Wei Zhao, Yuanyuan Niu, Yiran Peng, Min School of Urban Construction and Transportation Hefei University China Anhui Province Transportation Big Data Analysis and Application Engineering Laboratory China Anhui Province Ordinary University Key Laboratory of Traffic Information and Security China

ISBN: (纸本)9781510660151

With the rapid development of China's economy, the development speed and scale of transportation engineering have also expanded rapidly. But the problem of environmental pollution problems have also gradually emerged, and the use of environmental protection materials has become an inevitable trend of green transportation development. This paper puts forward the traffic optimization method at five-way intersection based on green building materials and signal processing. Firstly, the green and environment protection hot-melt reflective marking paint and color asphalt concrete pavement materials are used to construct the travel space of motor vehicles, non-motor vehicles and pedestrians at five-way intersection. Then, on this basis, the phase design method based on clipping method and the corresponding signal timing method are proposed to optimize the traffic flow travel time at five-way intersection. Finally, the evaluation and analysis is done by the VISSIM traffic simulation software, the results show that this method based on green building materials effectively defines the travel space of five-way intersection. On this premise, the traffic efficiency is further improved through signal processing optimization technology, which effectively reduces the number of conflict point at the five-way intersection and provides a basis for the research on the optimal control of deformed intersections based on green building materials and signal processing. © 2022 SPIE.

关键词： Computer software

来源：评论

学校读者我要写书评

暂无评论

Clause-level Relationship-aware Math Word Problems Solver

引用

Machine Intelligence Research 2022年第5期19卷 425-438页

作者： Chang-Yang Wu Xin Lin Zhen-Ya Huang Yu Yin Jia-Yu Liu Qi Liu Gang Zhou Anhui Province Key Laboratory of Big Data Analysis and Application School of Data ScienceUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Laboratory of Mathematical Engineering and Advanced Computing Information Engineering UniversityZhengzhou 450001China

Automatically solving math word problems,which involves comprehension,cognition,and reasoning,is a crucial issue in artificial intelligence *** math word problem solvers mainly work on word-level relationship extraction and the generation of expression solutions while lacking consideration of the clause-level *** this end,inspired by the theory of two levels of process in comprehension,we propose a novel clause-level relationship-aware math solver(CLRSolver)to mimic the process of human comprehension from lower level to higher ***,in the lower-level processes,we split problems into clauses according to their natural division and learn their *** the higher-level processes,following human′s multi-view understanding of clause-level relationships,we first apply a CNN-based module to learn the dependency relationships between clauses from word relevance in a local ***,we propose two novel relationship-aware mechanisms to learn dependency relationships from the clause semantics in a global ***,we enhance the representation of clauses based on the learned clause-level dependency *** expression generation,we develop a tree-based decoder to generate the mathematical *** conduct extensive experiments on two datasets,where the results demonstrate the superiority of our framework.

关键词： Artificial intelligence(AI) artificial neural network(ANN) computational mathematics machine intelligence machine learning

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：