检索结果-内蒙古大学图书馆

National Science Review 2024年第8期11卷 39-47页

作者： Ke Tang Xin Yao Department of Computer Science and Engineering Southern University of Science and Technology Department of Computing and Decision Sciences Lingnan University

Most optimization problems of practical significance are typically solved by highly configurable parameterized *** achieve the best performance on a problem instance,a trial-and-error configuration process is required,which is very costly and even prohibitive for problems that are already computationally intensive,*** problems associated with machine learning *** the past decades,many studies have been conducted to accelerate the tedious configuration process by learning from a set of training *** article refers to these studies as learn to optimize and reviews the progress achieved.

关键词： optimization data-driven algorithm design automated algorithm configuration machine learning

来源：评论

学校读者我要写书评

暂无评论

A Genetic Approach to Solve the MultiCriteria Anti-Clustering Problem

A Genetic Approach to Solve the MultiCriteria Anti-Clusterin...

引用

2023 IEEE International Conference on Industrial engineering and engineering Management, IEEM 2023

作者： Chassagne, A. De Smet, Y. Université Libre de Bruxelles Computer and Decision Engineering Department Belgium

ISBN: (纸本)9798350323153

We consider decision problems involving the simultaneous optimization of conflicting criteria. In this context, we introduce the notion of anti-clustering. One looks to a partition of objects characterized by a high level of intra-group heterogeneity and a high level of inter-group homogeneity. This goal is in opposition with traditional clustering methods. In addition, it is related to the notion of fairness in clustering. We propose a first implementation based on a genetic algorithm and compare it to random algorithms on illustrative data sets such as the academic ranking of world universities. Tests are performed to fine-tune the algorithm's parameters. © 2023 IEEE.

关键词： Clustering Fairness Genetic Algorithms Multiple Criteria decision Aid

来源：评论

学校读者我要写书评

暂无评论

Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training 41

Fault Tolerant ML: Efficient Meta-Aggregation and Synchronou...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Dahan, Tehila Levy, Kfir Y. Department of Data and Decision Sciences Technion Haifa Israel Department of Electrical and Computer Engineering Technion Haifa Israel

In this paper, we investigate the challenging framework of Byzantine-robust training in distributed machine learning (ML) systems, focusing on enhancing both efficiency and practicality. As distributed ML systems become integral for complex ML tasks, ensuring resilience against Byzantine failures-where workers may contribute incorrect updates due to malice or error-gains paramount importance. Our first contribution is the introduction of the Centered Trimmed Meta Aggregator (CTMA), an efficient meta-aggregator that upgrades baseline aggregators to optimal performance levels, while requiring low computational demands. Additionally, we propose harnessing a recently developed gradient estimation technique based on a double-momentum strategy within the Byzantine context. Our paper highlights its theoretical and practical advantages for Byzantine-robust training, especially in simplifying the tuning process and reducing the reliance on numerous hyperparameters. The effectiveness of this technique is supported by theoretical insights within the stochastic convex optimization (SCO) framework and corroborated by empirical evidence. 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

Density estimation-based method to determine sample size for random sample partition of big data

引用

Frontiers of computer Science 2024年第5期18卷 57-70页

作者： Yulin HE Jiaqi CHEN Jiaxing SHEN Philippe FOURNIER-VIGER Joshua Zhexue HUANG Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen 518107China College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060China Department of Computing and Decision Sciences Lingnan UniversityHong Kong 999077China

Random sample partition(RSP)is a newly developed big data representation and management model to deal with big data approximate computation *** research and practical applications have confirmed that RSP is an efficient solution for big data processing and ***,a challenge for implementing RSP is determining an appropriate sample size for RSP data *** a large sample size increases the burden of big data computation,a small size will lead to insufficient distribution information for RSP data *** address this problem,this paper presents a novel density estimation-based method(DEM)to determine the optimal sample size for RSP data ***,a theoretical sample size is calculated based on the multivariate Dvoretzky-Kiefer-Wolfowitz(DKW)inequality by using the fixed-point iteration(FPI)***,a practical sample size is determined by minimizing the validation error of a kernel density estimator(KDE)constructed on RSP data blocks for an increasing sample ***,a series of persuasive experiments are conducted to validate the feasibility,rationality,and effectiveness of *** results show that(1)the iteration function of the FPI method is convergent for calculating the theoretical sample size from the multivariate DKW inequality;(2)the KDE constructed on RSP data blocks with sample size determined by DEM can yield a good approximation of the probability density function(p.d.f);and(3)DEM provides more accurate sample sizes than the existing sample size determination methods from the perspective of *** demonstrates that DEM is a viable approach to deal with the sample size determination problem for big data RSP implementation.

关键词： random sample partition big data sample size Dvoretzky-Kiefer-Wolfowitz inequality kerneldensity estimator probability density function

来源：评论

学校读者我要写书评

暂无评论

Determining the 2-Tuple Total Domination Number of a Harary Graph under Specific Degree Conditions

引用

Journal of Information Science and engineering 2024年第2期40卷 253-264页

作者： Jao, Min-Shu Wang, Hung-Lung Chang, Jou-Ming Wu, Chia-Wen Department of Computer Science and Information Engineering National Taiwan Normal University Taipei City116 Taiwan Institute of Information and Decision Sciences National Taipei University of Business Taipei City100 Taiwan

Given a graph G, a 2-tuple total dominating set is a vertex subset S such that every vertex has at least two neighbors in S. The cardinality of a minimum 2-tuple total dominating set is called the 2-tuple total domination number. In this paper, we determine the 2-tuple total domination numbers of Hm,n for m ∈ {3, 5}, where Hm,n stands for a Harary graph of n vertices with degree parameter m. © 2024 Institute of Information Science. All rights reserved.

关键词： 2-tuple total domination domination graph theory Harary graphs regular graphs

来源：评论

学校读者我要写书评

暂无评论

Anti-Matthew FL: Bridging the Performance Gap in Federated Learning to Counteract the Matthew Effect 27

Anti-Matthew FL: Bridging the Performance Gap in Federated L...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Gao, Jiashi Yao, Xin Wei, Xuetao Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Computing and Decision Sciences Lingnan University Hong Kong

ISBN: (纸本)9781643685489

Federated learning (FL) stands as a paradigmatic approach that facilitates model training across heterogeneous and diverse datasets originating from various data providers. However, conventional FLs fall short of achieving consistent performance, potentially leading to performance degradation for clients who are disadvantaged in data resources. Influenced by the Matthew effect, deploying a performance-imbalanced global model in applications further impedes the generation of high-quality data from disadvantaged clients, exacerbating the disparities in data resources among clients. In this work, we propose anti-Matthew fairness for the global model at the client level, requiring equal accuracy and equal decision bias across clients. To balance the trade-off between achieving anti-Matthew fairness and performance optimality, we formalize the anti-Matthew effect federated learning (anti-Matthew FL) as a multi-constrained multi-objectives optimization (MCMOO) problem and propose a three-stage multi-gradient descent algorithm to obtain the Pareto optimality. We theoretically analyze the convergence and time complexity of our proposed algorithms. Additionally, through extensive experimentation, we demonstrate that our proposed anti-Matthew FL outperforms other state-of-the-art FL algorithms in achieving a high-performance global model while effectively bridging performance gaps among clients. We hope this work provides valuable insights into the manifestation of the Matthew effect in FL and other decentralized learning scenarios and can contribute to designing fairer learning mechanisms, ultimately fostering societal welfare. © 2024 The Authors.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning with planning guardrails for building energydemand response

引用

Energy and AI 2023年第1期11卷 12-25页

作者： Doseok Jang Lucas Spangher Selvaprabu Nadarajah Costas Spanos Department of Electrical Engineering and Computer Science University of California at BerkeleyBerkeley94704CAUSA Department of Information and Decision Sciences University of Illinois at ChicagoChicago60607ILUSA

Building energy demand response is projected to be important in decarbonizing energy use. A demand responseprogram that communicates ‘‘artificial’’ hourly price signals to workers as part of a social game has the potentialto elicit energy consumption changes that simultaneously reduce energy costs and emissions. The efficacy ofsuch a program depends on the pricing agent’s ability to learn how workers respond to prices and mitigatethe risk of high energy costs during this learning process. We assess the value of deep reinforcement learning(RL) for mitigating this risk. Specifically, we explore the value of combining: (i) a model-free RL method thatcan learn by posting price signals to workers, (ii) a supervisory ‘‘planning model’’ that provides a syntheticlearning environment, and (iii) a guardrail method that determines whether a price should be posted to realworkers or the planning environment for feedback. In a simulated medium-sized office building, we compareour pricing agent against existing model-free and model-based deep RL agents, and the simpler strategy ofpassing on the time-of-use price signal to workers. We find that our controller eliminates 175,000 US Dollarsin initial investment, decreases by 30% the energy cost, and curbs emissions by 32% compared to energyconsumption under the time-of-use rate. In contrast, the model-free and model-based deep RL benchmarksare unable to overcome initial learning costs. Our results bode well for risk-aware deep RL facilitating thedeployment of building demand response.

关键词： Deep reinforcement learning Risk-aware planning Demand response Energy Decarbonization

来源：评论

学校读者我要写书评

暂无评论

Security and Energy Efficiency Enhancement for the Internet of Things: Challenges, Architecture and Future Research

Security and Energy Efficiency Enhancement for the Internet ...

引用

International Conference on Data Science and Network engineering, ICDSNE 2023

作者： Dewan, Ritu Nagpal, Tapsi Ahmad, Sharik Rana, Arun Kumar Islam, Sardar M. N. Department of Computer Science and Engineering Lingayas Vidyapeeth Faridabad India Department of Computer Science and Engineering Galgotias College of Engineering & Technology Gr. Noida India SILC Decision Sciences and Modelling Program Victoria University Victoria Australia

ISBN: (纸本)9789819967544

Thanks to constantly advancing technology, the world is changing rapidly. One such idea that has contributed to the reality of automation is the Internet of Things (IoT). IoT links various non-living objects to the internet and enables them to communicate with their local network to automate processes and simplify people’s lives. The IoT’s potential needs to be completely realised despite the enormous efforts of standards, organisations, coalitions, businesses, academics and others. A number of problems remain. The enabling technology, applications and business models, as well as the social and environmental repercussions, should all be taken into consideration while analysing these difficulties. This article’s emphasis is on unresolved issues and challenges from a technological perspective. The main objective is to provide a thorough evaluation of IoT in terms of energy and security, as well as unresolved problems and obstacles that need further study. We provide some perspectives on some new concepts to help future research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Decentralized control in active distribution grids via supervised and reinforcement learning

引用

Energy and AI 2024年第2期16卷 137-149页

作者： Stavros Karagiannopoulos Petros Aristidou Gabriela Hug Audun Botterud Laboratory for Information and Decision Systems(LIDS) Massachusetts Institute of TechnologyCambridgeUSA EEH-Power Systems Laboratory ETH Zurichhysikstrasse 38092 ZurichSwitzerland Department of Electrical Engineering Computer Engineering&InformaticsCyprus

While moving towards a low-carbon, sustainable electricity system, distribution networks are expected to host a large share of distributed generators, such as photovoltaic units and wind turbines. These inverter-based resources are intermittent, but also controllable, and are expected to amplify the role of distribution networks together with other distributed energy resources, such as storage systems and controllable loads. The available control methods for these resources are typically categorized based on the available communication network into centralized, distributed, and decentralized or local. Standard local schemes are typically inefficient, whereas centralized approaches show implementation and cost concerns. This paper focuses on optimized decentralized control of distributed generators via supervised and reinforcement learning. We present existing state-of-the-art decentralized control schemes based on supervised learning, propose a new reinforcement learning scheme based on deep deterministic policy gradient, and compare the behavior of both decentralized and centralized methods in terms of computational effort, scalability, privacy awareness, ability to consider constraints, and overall optimality. We evaluate the performance of the examined schemes on a benchmark European low voltage test system. The results show that both supervised learning and reinforcement learning schemes effectively mitigate the operational issues faced by the distribution network.

关键词： Supervised learning Reinforcement learning Deep deterministic policy gradient Decentralized control Active distribution systems

来源：评论

学校读者我要写书评

暂无评论

Feature Attribution Explanation Based on Multi-Objective Evolutionary Learning

Feature Attribution Explanation Based on Multi-Objective Evo...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Wang, Ziming Huang, Changwu Yao, Xin Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Computing and Decision Sciences Lingnan University Tuen Mun Hong Kong

ISBN: (纸本)9798400704956

Feature attribution explanation (FAE) method, which reveals the contribution of each input feature to the model's output, is one of the most popular explainable artificial intelligence techniques. To assess the quality of explanations provided by FAE methods, various metrics spanning multiple dimensions have been introduced. However, current FAE approaches often prioritize faithfulness of their explanations, neglecting other crucial aspects. To address this issue, we define the construction of a FAE explainable model as a multi-objective learning problem and propose a framework that simultaneously considers multiple quality metrics during FAE explanation generation. Our experimental results demonstrate that our approach outperforms existing FAE methods in terms of faithfulness, sensitivity, and complexity. Moreover, our method has better diversity and the capacity to offer different explanations for different *** paper for the Hot-off-the-Press track at GECCO 2024 summarizes the work Ziming Wang, Changwu Huang, Yun Li, and Xin Yao: Multi-objective Feature Attribution Explanation for Explainable Machine Learning published in ACM Transactions on Evolutionary Learning and Optimization [5]. © 2024 Copyright held by the owner/author(s).

关键词： Contrastive 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：