检索结果-内蒙古大学图书馆

Multi-objective optimization for assigning reviewers to proposals based on social networks

Journal of Management science and Engineering 2024年第3期9卷 419-439页

作者： Xing-Gang Luo Hong-Jie Li Zhong-Liang Zhang Wei Jiang School of Management Hangzhou Dianzi UniversityHangzhou310018China Experimental Center of Data Science and Intelligent Decision-Making Hangzhou Dianzi UniversityHangzhou310018China Antai College of Economics and Management Shanghai Jiao Tong UniversityShanghai200240China

Most of the literature on reviewer assignment problem(RAP)considers fitness or efficiency as the evaluation criterion of an assignment,e.g.,the degree of matching between reviewers and *** this study,we consider fairness of an assignment and establish two multi-objective linear integer programming models for proposal *** introduce a definition of fairness based on the closeness of social relationships between *** closeness of social relationships is quantified based on social networks among reviewers and serves as part of objective *** improved space-partitioning algorithm is designed to solve the multi-objective models with integer *** the problem size is large,two meta-heuristic algorithms are *** on real and randomly generated cases are provided to illustrate the effectiveness of the proposed models and algorithms.

关键词： Assignment Social network Multi-objective optimization Space-partitioning

来源：评论

学校读者我要写书评

暂无评论

A Novel Cross-organization Privacy Protection Method Based on Federated Learning 23

A Novel Cross-organization Privacy Protection Method Based o...

引用

6th International Conference on Information Management and Management science, IMMS 2023

作者： Yin, Wanting Sun, Yixin Li, Xinda Song, Rongjia State Grid Energy Research Institute Co. Ltd. China Experimental Center of Data Science and Intelligent Decision Making Hangzhou Dianzi University China

ISBN: (纸本)9798400707681

With the continuous development of science and technology, the degree of information in today's world is deepening, and the value of data information is becoming more and more important. At the same time, with the advancement of economic globalization, more and more users or business needs go beyond the traditional organizational boundaries, requiring multiple organizations to cooperate, and cross-organizational business management comes into being. Under the scenario of cross-organizational cooperation, protecting the business and data privacy of each organization has become a challenging task. Federated learning, as a new technology in the field of artificial intelligence, deals with both "data islands"and privacy protection. It can combine scattered data for training while maintaining the data privacy of each participating organization, and to a great extent, it protects sensitive data that needs to be fused. It has gradually become an effective means to solve the data and business privacy in cross-organizational business processes. This paper will combine federated learning to propose a cross-organizational privacy protection method based on federated learning to realize the privacy protection in cross-organizational business processes, and discuss the current challenges and future development direction to promote the further development of cross-organizational privacy protection methods. © 2023 ACM.

关键词： Informatization

来源：评论

学校读者我要写书评

暂无评论

Process Predictive Monitoring Based on Federated Learning: Challenges and Architecture Proposal 23

Process Predictive Monitoring Based on Federated Learning: C...

引用

6th International Conference on Information Management and Management science, IMMS 2023

ISBN: (纸本)9798400707681

Process predictive monitoring refers to prediction the future activities, execution time, resources and other attribute in the ongoing business process. Aiming at the problem that the data scale of a single enterprise or organization is limited in business process, the learning model is difficult to further improve the prediction ability. This paper proposes a novel process predictive monitoring architecture proposal based on federated learning, and applies federated learning in process predictive monitoring to avoid the original data transmission and protect the privacy of data. Through aggregation training, the diversity of data is increased and the generalization ability and prediction performance of the model are improved. © 2023 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The Price of Fairness for Budget-Feasible EF1 Allocations 17th

The Price of Fairness for Budget-Feasible EF1 Allocations

引用

17th International Conference on Combinatorial Optimization and Applications, COCOA 2024

作者： Hu, Tingwei Mei, Lili Wang, Zhen Zhang, Guochuan College of Computer Science Zhejiang University Hangzhou310027 China School of Cyberspace Hangzhou Dianzi University Hangzhou310018 China Experimental Center of Data Science and Intelligent Decision-Making Hangzhou Dianzi University Hangzhou310018 China

ISBN: (纸本)9789819644445

Fair allocation of indivisible items among agents with budget constraints has received considerable attention recently. In this model, each agent has a budget, and each item has a specific size and homogeneous or heterogeneous valuations for all the agents. In a fair allocation, each agent receives a bundle of items with total size no more than her budget, meanwhile the EF1 (envy-freeness up to one item) fairness holds between any agents. To avoid a trivial and meaningless solution in which all bundles are empty, we invoke the well-studied concept PoF (price of fairness), the worst-case ratio between the maximum total valuation without and with the fairness guarantee to capture the efficiency loss induced by fairness. In this paper, the PoFs are extensively studied in various settings. We first investigate an algorithm outputting an EF1 allocation with the total valuation at least 12n of the maximum total valuation (without EF1 requirement), where n is the number of agents. It implies that PoF is at most 2n. Meanwhile, we give an instance to show that PoF is at least n-ϵ. Then a special case that the valuation of an item is identical for all the agents is considered. We establish an algorithm which outputs an EF1 allocation with the total valuation at least 12 of the maximum total valuation. That is to say, an algorithm with PoF of 2 is devised. And we give a lower bound of 2-1n. Finally, the scenario of two agents is discussed. An algorithm with PoF of 32 is constructed when all the agents have identical valuation for an item. For different valuations, we improve the upper bound of PoF to 3. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Can Gaussian Sketching Converge Faster on a Preconditioned Landscape? 41

Can Gaussian Sketching Converge Faster on a Preconditioned L...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Yilong Ye, Haishan Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China Singapore College of Computing and Data Science NTU Singapore

This paper focuses on the large-scale optimization which is very popular in the big data era. The gradient sketching is an important technique in the large-scale optimization. Specifically, the random coordinate descent algorithm is a kind of gradient sketching method with the random sampling matrix as the sketching matrix. In this paper, we propose a novel gradient sketching called GSGD (Gaussian Sketched Gradient Descent). Compared with the classical gradient sketching methods such as the random coordinate descent and SEGA (Hanzely et al., 2018), our GSGD does not require the importance sampling but can achieve a fast convergence rate matching the ones of these methods with importance sampling. Furthermore, if the objective function has a non-smooth regularization term, our GSGD can also exploit the implicit structure information of the regularization term to achieve a fast convergence rate. Finally, our experimental results substantiate the effectiveness and efficiency of our algorithm. Copyright 2024 by the author(s)

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods 41

Double Stochasticity Gazes Faster: Snap-Shot Decentralized S...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Di, Hao Ye, Haishan Chang, Xiangyu Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China College of Computing and Data Science NTU Singapore Singapore

In decentralized optimization, m agents form a network and only communicate with their neighbors, which gives advantages in data ownership, privacy, and scalability. At the same time, decentralized stochastic gradient descent (SGD) methods, as popular decentralized algorithms for training large-scale machine learning models, have shown their superiority over centralized counterparts. Distributed stochastic gradient tracking (DSGT) (Pu & Nedić, 2021) has been recognized as the popular and state-of-the-art decentralized SGD method due to its proper theoretical guarantees. However, the theoretical analysis of DSGT (Koloskova et al., 2021) shows that its iteration complexity is (equation presented) where the doubly stochastic matrix W represents the network topology and CW is a parameter that depends on W. Thus, it indicates that the convergence property of DSGT is heavily affected by the topology of the communication network. To overcome the weakness of DSGT, we resort to the snapshot gradient tracking skill and propose two novel algorithms, snap-shot DSGT (SS DSGT) and accelerated snap-shot DSGT (ASS DSGT). We further justify that SS DSGT exhibits a lower iteration complexity compared to DSGT in the general communication network topology. Additionally, ASS DSGT matches DSGT's iteration complexity (equation presented) under the same conditions as DSGT. Numerical experiments validate SS DSGT's superior performance in the general communication network topology and exhibit better practical performance of ASS DSGT on the specified W compared to DSGT. Copyright 2024 by the author(s)

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

The impact of high-speed railway construction on regional economic development in Hubei Province

引用

Management System Engineering 2024年第1期3卷 1-21页

作者： Chen, Yajuan Lv, Yuejiao Zhang, Yanjie School of Management Wuhan University of Technology Wuhan China Research Center for Data Science and Intelligent Decision Making Wuhan University of Technology Wuhan China

Based on the panel data of 16 cities in Hubei Province from 2009 to 2019 (excluding the data during Covid-19 pandemic period), we construct multi-temporal difference-in-differences model (DID) and Spatial Durbin model (SDM) to explore the impact of the High-speed Railway (HSR) construction on the regional economic development in terms of direct economic effect, indirect economic effect and spatial spillover effect. The main conclusions of this paper are as follows: firstly, HSR construction promotes the economic development of cities in Hubei Province in a long time and in a large spatial scope. And the impacts on the economic development are significantly heterogeneous among different types of cities. Also, HSR construction has widened the economic development gap among cities to some extent. Secondly, the upgrading of an industrial structure and the improvement of urbanization level both play mediating roles in the economic impact of HSR construction. Thirdly, the HSR construction has significant spatial spillover effect on economic development, but the spillover effect becomes insignificant with the increase of distance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Urban system equilibrium model in an asymmetric polycentric city and the influence of rail transit investment

引用

Management System Engineering 2024年第1期3卷 1-16页

作者： Chen, Yajuan Tian, Xin Huang, Han School of Management Wuhan University of Technology Wuhan China Research Center for Data Science and Intelligent Decision Making Wuhan University of Technology Wuhan China

Taking bus and subway into account, an asymmetric polycentric urban system equilibrium model is constructed to explore the impacts of rail transit on the distribution of residents and labor force in a linear polycentric urban system. By comparing the urban system equilibria before and after the introduction of rail transit, the influence of rail transit on urban performance is analyzed. The results show that the introduction of rail transit makes the advantaged center more attractive for the labor force, and further widens the economic level gap between the two business centers. Specifically, larger distance between the two commercial centers and the higher subway travel cost would strengthen the polarization effect caused by rail transit investment. Since the improvement of transportation makes it easier for residents to accept long-distance commuting and they are more willing to choose the jobs in the advanced center.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time series prediction and application based on multi-kernel support vector regression 2

Time series prediction and application based on multi-kernel...

引用

2nd International Symposium on Computer Applications and Information Systems, ISCAIS 2023

作者： Yi, Xiaoxing Wen, Xueting Yin, Xiangfeng School of Mathematics and Computational Science Hunan University of Science and Technology Hunan province Xiangtan China School of Mathematics and Computational Science Hunan University of Science and Technology Hunan Engineering Research Center for Big Data and Intelligent Decision-making of Industrial Development Hunan province Xiangtan China

ISBN: (纸本)9781510666665

In this paper, we propose a new MRMRKA-SVR-GARCH model to predict the volatility of time series. This model is a combination of the MRMRKA-SVR model and the GARCH model. Since SVR-GARCH model has been successfully employed to forecast volatility. Empirical results show that the multi-kernel support vector regression based on minimal redundancy maximal correlation criteria and kernel target alignment (MRMRKA-SVR) tend to beat single-kernel SVR models in terms of forecasting accuracy. First,we use the MRMRKA algorithm to select a set of kernels to establish a multi-kernel, and establish the MRMRKA-SVR model. Then we use MRMRKA-SVR to estimate the volatility equation of GARCH model, and establish MRMRKA-SVR-GARCH model. Furthermore, the models’ predictive ability was evaluated using three empirical analysises on China Unicom’s stock price data and stock price data of ICBC. Under different basic kermel numbers m, compare the prediction errors between the proposed model and the SVR-GARCH model based on the mixed Gaussian kernels in the two stock data, the results show that the prediction accuracy of the MRMRKA-SVR-GARCH model fluctuates slightly with the change of m, and the MAE and RMSE of the MRMRKASVR- GARCH model are lower than the mixed-Gaussian-kernel SVR-GARCH model . Description MRMRKA-SVRGARCH model managed to outperform the mixed-Gaussian-kernel SVR-GARCH model. Threrfore, the MRMRKASVR- GARCH model can provide a certain degree of reference in analyzing the trend and prediction of volatility, and has high feasibility and effectiveness. © 2023 SPIE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient 41

Double Variance Reduction: A Smoothing Trick for Composite O...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Di, Hao Ye, Haishan Zhang, Yueling Chang, Xiangyu Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China International Business School Beijing Foreign Studies University Beijing China Singapore College of Computing and Data Science NTU Singapore

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods encounter an additional variance called the coordinate-wise variance, which stems from the random gradient estimation. To reduce this variance, prior works require estimating all partial derivatives, essentially approximating FO information. This approach demands O(d) function evaluations (d is the dimension size), which incurs substantial computational costs and is prohibitive in high-dimensional scenarios. This paper proposes the Zeroth-order Proximal Double Variance Reduction (ZPDVR) method, which utilizes the averaging trick to reduce both sampling and coordinate-wise variances. Compared to prior methods, ZPDVR relies solely on random gradient estimates, calls the stochastic zeroth-order oracle (SZO) in expectation O(1) times per iteration, and achieves the optimal O(d(n+κ) log(1/ϵ)) SZO query complexity in the strongly convex and smooth setting, where κ represents the condition number and ϵ is the desired accuracy. Empirical results validate ZPDVR's linear convergence and demonstrate its superior performance over other related methods. Copyright 2024 by the author(s)

关键词： Stochastic systems

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：