检索结果-内蒙古大学图书馆

2018 SIAM International Conference on data Mining, SDM 2018

作者： Jin, Tianyuan Xu, Tong Zhong, Hui Chen, Enhong Wang, Zhefeng Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application University of Science and Technology of China China

With the development of social networking services, social influence analyses, as well as the influence maximization tasks, have attracted wide attention in both academia and industry. Traditional studies mainly focus on simulating process of influence spread. However, two basic functions of social spread, i.e., information propagation and information adoption have not been clearly distinguished. Usually, as information adoption could be even more significant for information publishers in application scenarios, more comprehensive analysis for effect of adoption is urgently required. To that end, in this paper, we propose a novel framework to generally describe social spread, in which information adoption process is separately formulated as random events. Along this line, when we apply this framework to the information adoption maximization task, with proving that the adoption maximization problem is NP-hard and submodular, we further design a polling-based algorithm to achieve an effective approximation. Extensive experiments on four real-world data sets demonstrate the effectiveness and efficiency of proposed algorithms, which validates that our approach could better summarize the complete social spread process, and further support the necessity of distinguishing information adoption from information propagation. © 2018 by SIAM.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Tracing Knowledge Instead of Patterns: Stable Knowledge Tracing with Diagnostic Transformer 23

Tracing Knowledge Instead of Patterns: Stable Knowledge Trac...

引用

2023 World Wide Web Conference, WWW 2023

作者： Yin, Yu Dai, Le Huang, Zhenya Shen, Shuanghong Wang, Fei Liu, Qi Chen, Enhong Li, Xin Anhui Key Lab. of Big Data Analysis and Application University of Science and Technology of China State Key Lab. of Cognitive Intelligence Anhui Hefei China University of Science and Technology of China IFLYTEK Co. Ltd China

ISBN: (纸本)9781450394161

Knowledge Tracing (KT) aims at tracing the evolution of the knowledge states along the learning process of a learner. It has become a crucial task for online learning systems to model the learning process of their users, and further provide their users a personalized learning guidance. However, recent developments in KT based on deep neural networks mostly focus on increasing the accuracy of predicting the next performance of students. We argue that current KT modeling, as well as training paradigm, can lead to models tracing patterns of learner's learning activities, instead of their evolving knowledge states. In this paper, we propose a new architecture, Diagnostic Transformer (DTransformer), along with a new training paradigm, to tackle this challenge. With DTransformer, we build the architecture from question-level to knowledge-level, explicitly diagnosing learner's knowledge proficiency from each question mastery states. We also propose a novel training algorithm based on contrastive learning that focuses on maintaining the stability of the knowledge state diagnosis. Through extensive experiments, we will show that with its understanding of knowledge state evolution, DTransformer achieves a better performance prediction accuracy and more stable knowledge state tracing results. We will also show that DTransformer is less sensitive to specific patterns with case study. We open-sourced our code and data at https://***/yxonic/DTransformer. © 2023 ACM.

关键词： Deep neural networks

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

Comprehensive urban atlas design and practice of big spatiotemporal data 29

Comprehensive urban atlas design and practice of big spatiot...

引用

29th International Conference on Geoinformatics, Geoinformatics 2022

作者： Jing, Xin Wen, Zhang Xin, Luo Shanghai Surveying and Mapping Institute China Mnr Key Lab. of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities Shanghai China

ISBN: (数字)9798350309881

ISBN: (纸本)9798350309881

In view of spatiotemporal big data to compile comprehensive urban atlas that highlights urban personality and regional characteristics, this paper starts with the characteristics of big spatiotemporal data, analyzes the mapping logic architecture and mapping expression form of urban comprehensive atlas, and then takes Atlas of Shanghai as an example to carry out the practice and analysis of map compilation with big data, in order to provide some reference for urban atlas design. © 2022 IEEE.

关键词： big data

来源：评论

学校读者我要写书评

暂无评论

Research and practice of natural resources monitoring and linkage updating technology: A case study of Shanghai 29

Research and practice of natural resources monitoring and li...

引用

29th International Conference on Geoinformatics, Geoinformatics 2022

作者： Wen, Zhang Jing, Xin Yao, Lu Shanghai Surveying and Mapping Institute China Key Lab. of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities Mnr Shanghai China

ISBN: (数字)9798350309881

ISBN: (纸本)9798350309881

With the national proposal and promotion of ecological civilization construction, the demand for natural resources monitoring application services with unified management of natural resources has become increasingly strong. In this paper, we reviewed the current situation of domestic natural resource monitoring and linkage updating technology and proposed a set of natural resource monitoring and linkage updating technology frameworks based on the demand of natural resource management. The feasibility of the framework is verified by being applied to Shanghai, which solves the application demand of high frequency and multi-thematic natural resource elements monitoring in the process of urban management in Shanghai. We integrated the natural and management attributes of natural resources based on the database linkage update, coordinated the monitoring, management, database construction, and sharing applications of natural resources, providing an important reference for natural resource monitoring and data application sharing. © 2022 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Multimodal Dialogue Systems via Capturing Context-aware Dependencies of Semantic Elements 20

Multimodal Dialogue Systems via Capturing Context-aware Depe...

引用

28th ACM International Conference on Multimedia, MM 2020

作者： He, Weidong Li, Zhi Lu, Dongcai Chen, Enhong Huai, Baoxing Yuan, Jing Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China School of Data Science University of Science and Technology of China China HUAWEI Technologies Hangzhou China

ISBN: (纸本)9781450379885

Recently, multimodal dialogue systems have engaged increasing attention in several domains such as retail, travel, etc. In spite of the promising performance of pioneer works, existing studies usually focus on utterance-level semantic representations with hierarchical structures, which ignore the context-aware dependencies of multimodal semantic elements, i.e., words and images. Moreover, when integrating the visual content, they only consider images of the current turn, leaving out ones of previous turns as well as their ordinal information. To address these issues, we propose a Multimodal diAlogue systems with semanTic Elements, MATE for short. Specifically, we unfold the multimodal inputs and devise a Multimodal Element-level Encoder to obtain the semantic representation at element-level. Besides, we take into consideration all images that might be relevant to the current turn and inject the sequential characteristics of images through position encoding. Finally, we make comprehensive experiments on a public multimodal dialogue dataset in the retail domain, and improve the BLUE-4 score by 9.49, and NIST score by 1.8469 compared with state-of-the-art methods. © 2020 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unavailab.e time aware scheduling of hybrid task on heterogeneous distributed system

引用

IAENG International Journal of Applied Mathematics 2020年第1期50卷 133-146页

作者： Xuan, Hejun Wei, Shiwei Zhao, Xuelin Zhou, Yang Ma, Xingpo Liu, Daohua Li, Yanling School of Computer and Information Technology Xinyang Normal University Henan Xinyang China School of Computer and Technology Guilin University of Aerospace Technology Guilin541000 China Henan Key Lab. of Analysis and Application of Education Big Data Xinyang Normal University Henan Xinyang464000 China

The resource allocation for tasks in heterogeneous distributed system is a well known NP-hard problem. For the sake of making the makespan is minimized, it is hard to distribute the tasks to proper processors. The problem is even more complex and challenging when the processors have unavailab.e time and the tasks type are various. This paper investigates a resource allocation problem for hybrid tasks comprising both divisible and bag-of-tasks(BoT) in heterogeneous distributed system when the processors has unavailab.e time. First, the mathematical model, which minimizes the makespan of the hybrid tasks when the processors have unavailab.e time, is established. Second, we propose a scheduling algorithm referred to as bag-of-tasks allocate-pull and divisible task allocation (BoTAPDTA) algorithm for handling hybrid tasks on heterogeneous distributed systems. In addition, to solving the optimization model efficiently, a generic algorithm(GA) is proposed. For the sake of reducing the search space and solving the optimization model effectively, a two step scheduling algorithm(TSGA), which first allocate bag-of-tasks(BoT) using generic algorithm and then assign divisible task to processors like BoTAPDTA, is designed. Finally, numerical simulation experiments are conducted, and experimental results indicate the effectiveness of the proposed model and algorithm. © 2020.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Maximizing Monotone DR-submodular Continuous Functions by Derivative-free Optimization

arXiv

引用

arXiv 2018年

作者： Zhang, Yibo Qian, Chao Tang, Ke Anhui Province Key Lab of Big Data Analysis and Application Ustc Shenzhen Key Lab of Computational Intelligence SUSTech

In this paper, we study the problem of monotone (weakly) DR-submodular continuous maximization. While previous methods require the gradient information of the objective function, we propose a derivative-free algorithm LDGM for the first time. We define and to characterize how close a function is to continuous DR-submodulr and submodular, respectively. Under a convex polytope constraint, we prove that LDGM can achieve an (1 e)-Approximation guarantee after O(1=) iterations, which is the same as the best gradient-based algorithm. Moreover, in some special cases, a variant of LDGM can achieve an (=2)(1 e)-Approximation guarantee for (weakly) submodular functions. We also give theoretical results showing that a generalization of LDGM is robust under additive noise or in stochastic settings. Empirical results on budget allocation and maximum coverage verify the effectiveness of LDGM. Copyright © 2018, The Authors. 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

MOLECULE GENERATION FOR TARGET PROTEIN BINDING WITH STRUCTURAL MOTIFS 11

MOLECULE GENERATION FOR TARGET PROTEIN BINDING WITH STRUCTUR...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Zhang, Zaixi Min, Yaosen Zheng, Shuxin Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Institute of Interdisciplinary Information Sciences Tsinghua University China Microsoft Research United States

Designing ligand molecules that bind to specific protein binding sites is a fundamental problem in structure-based drug design. Although deep generative models and geometric deep learning have made great progress in drug design, existing works either sample in the 2D graph space or fail to generate valid molecules with realistic substructures. To tackle these problems, we propose a Fragment-based LigAnd Generation framework (FLAG), to generate 3D molecules with valid and realistic substructures fragment-by-fragment. In FLAG, a motif vocabulary is constructed by extracting common molecular fragments (i.e., motif) in the dataset. At each generation step, a 3D graph neural network is first employed to encode the intermediate context information. Then, our model selects the focal motif, predicts the next motif type, and attaches the new motif. The bond lengths/angles can be quickly and accurately determined by cheminformatics tools. Finally, the molecular geometry is further adjusted according to the predicted rotation angle and the structure refinement. Our model not only achieves competitive performances on conventional metrics such as binding affinity, QED, and SA, but also outperforms baselines by a large margin in generating molecules with realistic substructures. Our code is publicly availab.e at https://***/zaixizhang/FLAG. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Molecular property prediction: A multilevel quantum interactions modeling perspective

arXiv

引用

arXiv 2019年

作者： Lu, Chengqiang Liu, Qi Wang, Chao Huang, Zhenya Lin, Peize He, Lixin Anhui Province Key Lab. of Big Data Analysis and Application University of SandT of China Key Laboratory of Quantum Information University of SandT of China

Predicting molecular properties (e.g., atomization energy) is an essential issue in quantum chemistry, which could speed up much research progress, such as drug designing and substance discovery. Traditional studies based on density functional theory (DFT) in physics are proved to be time-consuming for predicting large number of molecules. Recently, the machine learning methods, which consider much rule-based information, have also shown potentials for this issue. However, the complex inherent quantum interactions of molecules are still largely underexplored by existing solutions. In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction. Specifically, we represent each molecule as a graph to preserve its internal structure. Moreover, the well-designed hierarchical graph neural network directly extracts features from the conformation and spatial information followed by the multilevel interactions. As a consequence, the multilevel overall representations can be utilized to make the prediction. Extensive experiments on both datasets of equilibrium and off-equilibrium molecules demonstrate the effectiveness of our model. Furthermore, the detailed results also prove that MGCN is generalizable and transferable for the prediction. Copyright © 2019, The Authors. All rights reserved.

关键词： Molecules

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：