检索结果-内蒙古大学图书馆

Automated algorithm selection: from Feature-Based to Feature-Free Approaches

JOURNAL OF HEURISTICS 2023年第1期29卷 1-38页

作者： Alissa, Mohamad Sim, Kevin Hart, Emma Edinburgh Napier Univ Sch Comp Edinburgh Scotland

We propose a novel technique for algorithm-selection, applicable to optimisation domains in which there is implicit sequential information encapsulated in the data, e.g., in online bin-packing. Specifically we train two types of recurrent neural networks to predict a packing heuristic in online bin-packing, selecting from four well-known heuristics. As input, the RNN methods only use the sequence of item-sizes. This contrasts to typical approaches to algorithm-selection which require a model to be trained using domain-specific instance features that need to be first derived from the input data. The RNN approaches are shown to be capable of achieving within 5% of the oracle performance on between 80.88 and 97.63% of the instances, depending on the dataset. They are also shown to outperform classical machine learning models trained using derived features. Finally, we hypothesise that the proposed methods perform well when the instances exhibit some implicit structure that results in discriminatory performance with respect to a set of heuristics. We test this hypothesis by generating fourteen new datasets with increasing levels of structure, and show that there is a critical threshold of structure required before algorithm-selection delivers benefit.

关键词： Deep learning Machine learning Recurrent neural network algorithm selection Bin-packing problem Feature-free approach

来源：评论

学校读者我要写书评

暂无评论

Recommender Systems algorithm selection for Ranking Prediction on Implicit Feedback Datasets 24

Recommender Systems Algorithm Selection for Ranking Predicti...

引用

18h ACM Conference on Recommender Systems (RecSys)

作者： Wegmeth, Lukas Vente, Tobias Beel, Joeran Univ Siegen Intelligent Syst Grp Siegen Germany

ISBN: (纸本)9798400705052

The recommender systems algorithm selection problem for ranking prediction on implicit feedback datasets is under-explored. Traditional approaches in recommender systems algorithm selection focus predominantly on rating prediction on explicit feedback datasets, leaving a research gap for ranking prediction on implicit feedback datasets. algorithm selection is a critical challenge for nearly every practitioner in recommender systems. In this work, we take the first steps toward addressing this research gap. We evaluate the NDCG@10 of 24 recommender systems algorithms, each with two hyperparameter configurations, on 72 recommender systems datasets. We train four optimized machine-learning meta-models and one automated machine-learning meta-model with three different settings on the resulting meta-dataset. Our results show that the predictions of all tested meta-models exhibit a median Spearman correlation ranging from 0.857 to 0.918 with the ground truth. We show that the median Spearman correlation between meta-model predictions and the ground truth increases by an average of 0.124 when the meta-model is optimized to predict the ranking of algorithms instead of their performance. Furthermore, in terms of predicting the best algorithm for an unknown dataset, we demonstrate that the best optimized traditional meta-model, e.g., XGBoost, achieves a recall of 48.6%, outperforming the best tested automated machine learning meta-model, e.g., AutoGluon, which achieves a recall of 47.2%.

关键词： algorithm selection Automated Recommender Systems AutoRecSys Ranking Prediction Collaborative Filtering

来源：评论

学校读者我要写书评

暂无评论

algorithm selection across algorithm Configurators A Case Study on Multi-objective Optimization

Algorithm Selection across Algorithm Configurators A Case St...

引用

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Misir, Mustafa Duke Kunshan Univ Div Nat & Appl Sci Kunshan Peoples R China

ISBN: (纸本)9781665487689

The present work utilizes algorithm selection for automatically specifying the parameter tuning method for a given tuning task. The idea of parameter tuning is motivated by the premature algorithm designs and their sub-optimal or poor parameter value choices. The decisions both on the designs and the parameter values are largely given based on the experiences of the developers or the target problem domain experts after a limited number of trials. While the existing tuning approaches tend to offer improvements over the default parameter values for varying algorithms, they can be computationally expensive. Additionally, there is no a single, ultimate parameter tuning strategy. These facts suggest to choose the most effective tuning algorithm for a specific scenario. This study utilizes an existing algorithm selection system to address this problem. The idea is to allocate potentially the most effective tuning method for a given task instead of relying on a single tuner. On that note, a group of well-known parameter configuration approaches are accommodated as the candidate methods to tune NSGA-II for solving a suite of multi-objective optimization benchmarks, referencing a recent article. The computational analysis revealed that algorithm selection outperforms those constituent parameter tuning methods when each is used as a standalone manner. Additionally, the dis/-similarity analysis carried on the problem instances / benchmarks give hints on the diversity level of the benchmarks. Furthermore, a similar inspection reported on the parameter tuning procedures show the behavioural resemblance between them.

关键词： algorithm selection algorithm configuration parameter tuning multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Learning dataset representation for automatic machine learning algorithm selection

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2022年第10期64卷 2599-2635页

作者： Cohen-Shapira, Noy Rokach, Lior Ben Gurion Univ Negev Software & Informat Syst Engn Dept Beer Sheva Israel Ben Gurion Univ Negev Data Sci Beer Sheva Israel Ben Gurion Univ Negev Dept Software & Informat Syst Engn SISE Beer Sheva Israel

The algorithm selection problem is defined as identifying the best-performing machine learning (ML) algorithm for a given combination of dataset, task, and evaluation measure. The human expertise required to evaluate the increasing number of ML algorithms available has resulted in the need to automate the algorithm selection task. Various approaches have emerged to handle the automatic algorithm selection challenge, including meta-learning. Meta-learning is a popular approach that leverages accumulated experience for future learning and typically involves dataset characterization. Existing meta-learning methods often represent a dataset using predefined features and thus cannot be generalized across different ML tasks, or alternatively, learn a dataset's representation in a supervised manner and therefore are unable to deal with unsupervised tasks. In this study, we propose a novel learning-based task-agnostic method for producing dataset representations. Then, we introduce TRIO, a meta-learning approach, that utilizes the proposed dataset representations to accurately recommend top-performing algorithms for previously unseen datasets. TRIO first learns graphical representations for the datasets, using four tools to learn the latent interactions among dataset instances and then utilizes a graph convolutional neural network technique to extract embedding representations from the graphs obtained. We extensively evaluate the effectiveness of our approach on 337 datasets and 195 ML algorithms, demonstrating that TRIO significantly outperforms state-of-the-art methods for algorithm selection for both supervised (classification and regression) and unsupervised (clustering) tasks.

关键词： AutoML algorithm selection Meta-learning Task-agnostic dataset representation

来源：评论

学校读者我要写书评

暂无评论

Adaptive local landscape feature vector for problem classification and algorithm selection

引用

APPLIED SOFT COMPUTING 2022年 131卷

作者： Li, Yaxin Liang, Jing Yu, Kunjie Chen, Ke Guo, Yinan Yue, Caitong Zhang, Leiyu Zhengzhou Univ Sch Elect Engn Zhengzhou 450001 Peoples R China China Univ Min & Technol Beijing 100084 Peoples R China

Fitness landscape analysis is a data-driven technique to study the relationship between problem characteristics and algorithm performance by characterizing the landscape features in the search space of an optimization problem. However, most of the existing landscape features still face poor in classifying the problems and low accuracy in selecting the most appropriate algorithm for a given problem. In this study, an adaptive local landscape feature vector (ALLFV) is proposed for problem classification and algorithm selection. Specifically, an adaptive discretization scheme is designed to calculate adaptive related parameters and construct the sequence between the fitness values of the search point and its nearest neighbors. By considering the frequencies of the same sequence values, the spatial structural information for the fitness landscape is computed as a feature vector according to the feature vector calculation mechanism. The experimental results tested on various problems demonstrate the excellence of ALLFV in terms of accuracy, stability, and computational cost. Moreover, ALLFV has shown superior practicality and reliability in the application of algorithm selection for numerical optimization problems. Consequently, ALLFV is well suited as an alternative for problem classification, as well as algorithm selection under excessive candidate optimization algorithms and limited prior knowledge of problems.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Continuous optimization Population-based algorithm Fitness landscape Problem classification algorithm selection

来源：评论

学校读者我要写书评

暂无评论

Meta-learning based industrial intelligence of feature nearest algorithm selection framework for classification problems

引用

JOURNAL OF MANUFACTURING SYSTEMS 2022年 62卷 767-776页

作者： Li, Li Wang, Yong Xu, Ying Lin, Kuo-Yi Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 201804 Peoples R China Beijing Wodong Tianjun Informat Technol Co Ltd Shanghai Branch Beijing Peoples R China

As more and more novel algorithms being proposed, it is difficult for engineers to choose suitable algorithms to solve engineering problems in manufacturing systems. According to the No Free Lunch theorems, there is no universal algorithm applicable to all problems. To solve the problem, this paper proposes a meta-learning based industrial intelligence of feature nearest algorithm selection framework for classification problems which are common in manufacturing. The proposed framework consists of three parts: dataset module, classification algorithms module and recommendation module. Firstly, 32 dataset characteristic measurement indicators are extracted based on meta-learning from 34 popular datasets. Then 13 common classification algorithms are applied in each dataset for algorithm optimizing. Through comparative analysis, it is found that the bat algorithm is better than the differential evolution algorithm in parameter optimization. Finally, in recommendation module, the relatively better algorithm is recommended to the new dataset according to the similarity between the new dataset and the reference datasets, which is measured by four distance methods. The result shows that the recommendation accuracy and hit rate of the new dataset are not less than 84.10 % and 85.29 % respectively, which can provide a good algorithm recommendation for engineers.

关键词： algorithm selection Meta-learning Classification problems Characteristic measurement indicators Similarity

来源：评论

学校读者我要写书评

暂无评论

Explainable algorithm selection for the Capacitated Lot Sizing Problem 1

引用

21st International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR)

作者： Visentin, Andrea Gallchoir, Aodh O. Kaercher, Jens Meyr, Herbert Univ Coll Cork Sch Comp Sci & IT Cork Ireland Insight SFI Res Ctr Data Analyt Cork Ireland Univ Hohenheim Dept Supply Chain Management Stuttgart Germany

ISBN: (数字)9783031605994

ISBN: (纸本)9783031606014;9783031605994

algorithm selection is a class of meta-algorithms that has emerged as a crucial approach for solving complex combinatorial optimization problems. Successful algorithm selection involves navigating a diverse landscape of solvers, each designed with distinct heuristics and search strategies. It is a classification problem in which statistical features of a problem instance are used to select the algorithm that should tackle it most efficiently. However, minimal attention has been given to investigating algorithm selection decisions. This work presents a framework for iterative feature selection and explainable multi-class classification in algorithm selection for the Capacitated Lot Sizing Problem (CLSP). The CLSP is a combinatorial optimization problem widely studied with important industrial applications. The framework reduces the features considered by the machine learning approach and uses SHAP analysis to investigate their contribution to the selection. The analysis shows which instance type characteristics positively affect the relative performance of a heuristic. The approach can be used to improve the algorithm selection's transparency and inform the developer of an algorithm's weak and strong points. The experimental analysis shows that the framework selector provides valuable insights with a narrow optimality gap close to a parallel deployment of the heuristic set that generalises well to instances considerably bigger than the training ones.

关键词： algorithm selection xAI Capacitated Lot Sizing Feature selection SHAP Analysis

来源：评论

学校读者我要写书评

暂无评论

Online metaheuristic algorithm selection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年第0期201卷 1页

作者： Meidani, Kazem Mirjalili, Seyedali Farimani, Amir Barati Carnegie Mellon Univ Dept Mech Engn Pittsburgh PA 15232 USA Torrens Univ Australia Ctr Artificial Intelligence Res & Optimizat Adelaide SA Australia Yonsei Univ Yonsei Frontier Lab Seoul South Korea Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA Carnegie Mellon Univ Dept Biomed Engn Pittsburgh PA 15213 USA

The performance of optimization algorithms significantly depends on the landscape of the problems. It is known that there is no single algorithm that outperforms others on problems with different fitness landscapes. One of the issues in metaheuristic algorithms is keeping the balance between exploration and exploitation. The features extracted from analysis of fitness landscapes can be used to select the suitable algorithm for the given problem. However, these features are usually expensive and extracted prior to the optimization process which leads to a single algorithm to be selected. In this work, we propose an intelligent switch mechanism that enjoys an efficient non-convex ratio (ENCR) feature extracted online during the optimization to switch between two choices of algorithms, each favoring a type of landscape in terms of modality. For this work, two case studies including a pair of Harris hawks optimizer (HHO) and differential evolution (DE) and another pair of multiverse optimizer (MVO) and moth-flame optimizer (MFO) are selected among several algorithms to evaluate the performance of this framework. The proposed one-way and two-way switch algorithms take advantage of the merits of the two base algorithms to reach better final solutions and higher convergence rates in the majority of case studies. The overall comparison and ranking of the algorithms, including a random switch baseline, demonstrates the superiority of the intelligent switch mechanisms over the baselines.

关键词： Metaheuristic optimization Fitness landscape analysis Efficient non-convex ratio algorithm selection Intelligent switch mechanism Adaptive algorithm Optimization algorithm Benchmark

来源：评论

学校读者我要写书评

暂无评论

An algorithm selection approach for the flexible job shop scheduling problem: Choosing constraint programming solvers through machine learning

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2022年第3期302卷 874-891页

作者： Mueller, David Mueller, Marcus G. Kress, Dominik Pesch, Erwin Univ Siegen Management Informat Sci Kohlbettstr 15 D-57068 Siegen Germany German Aerosp Ctr DLR Inst Robot & Mechatron Munchener Str 20 D-82234 Wessling Germany Helmut Schmidt Univ Univ Fed Armed Forces Hamburg Business Adm Especially Procurement & Prod Friedrich Ebert Damm 245 D-22159 Hamburg Germany HHL Leipzig Ctr Adv Studies Management Jahnallee 59 D-04109 Leipzig Germany

Constraint programming solvers are known to perform remarkably well for most scheduling problems. However, when comparing the performance of different available solvers, there is usually no clear winner over all relevant problem instances. This gives rise to the question of how to select a promising solver when knowing the concrete instance to be solved. In this article, we aim to provide first insights into this question for the flexible job shop scheduling problem. We investigate relative performance differences among five constraint programming solvers on problem instances taken from the literature as well as randomly generated problem instances. These solvers include commercial and non-commercial software and represent the state-of-the-art as identified in the relevant literature. We find that two solvers, the IBM ILOG CPLEX CP Optimizer and Google's OR-Tools, outperform alternative solvers. These two solvers show complementary strengths regarding their ability to determine provably optimal solutions within practically reasonable time limits and their ability to quickly determine high quality feasible solutions across different test instances. Hence, we leverage the resulting performance complementarity by proposing algorithm selection approaches that predict the best solver for a given problem instance based on instance features or parameters. The approaches are based on two machine learning techniques, decision trees and deep neural networks, in various variants. In a computational study, we analyze the performance of the resulting algorithm selection models and show that our approaches outperform the use of a single solver and should thus be considered as a relevant tool by decision makers in practice. (C) 2022 Elsevier B.V. All rights reserved.

关键词： Scheduling Constraint programming algorithm selection Machine learning Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Instance space analysis and algorithm selection for the job shop scheduling problem

引用

COMPUTERS & OPERATIONS RESEARCH 2022年 141卷 1页

作者： Strassl, Simon Musliu, Nysret TU Wien Christian Doppler Lab Artificial Intelligence & O DBAI Vienna Austria

This paper is concerned with the job shop scheduling problem, a well-known, NP-hard problem that has been extensively studied in the literature, but for which, despite its age and popularity, there has been relatively little work done towards understanding the landscape of instances. We provide a systematic analysis of the instance space for this problem. For this purpose, the benchmark instances commonly used in the literature were analyzed and extended by a set of newly generated instances of various sizes with processing times drawn from different probability distributions. A number of different state-of-the-art algorithms were evaluated on the extended instance set to analyze their performance patterns and highlight the differences to the current set of benchmark instances. It was found that the existing instances cover a significantly smaller area than the generated ones and did in fact result in different conclusions regarding the algorithms' performances. Furthermore, different algorithms have been shown to excel on distinct subsets of the extended instance set. This has been utilized to train machine learning models to predict the best algorithm for a given instance, the best of which was able to obtain the best solution for 90% of the instances, whereas the best individual algorithm only obtained the best solution for 64%.

关键词： Instance space analysis ISA Job shop scheduling Automated algorithm selection algorithm selection Job scheduling JSSP

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：