A Feature-Free Approach to Automated Algorithm Selection

被引:0
作者
Alissa, Mohamad [1 ]
Sim, Kevin [1 ]
Hart, Emma [1 ]
机构
[1] Edinburgh Napier Univ, Edinburgh, Midlothian, Scotland
来源
PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2023 COMPANION | 2023年
关键词
Deep Learning; Recurrent Neural Network; Algorithm Selection;
D O I
10.1145/3583133.3595832
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This article summarises recent work in the domain of feature-free algorithm selection that was published in the Journal of Heuristics in January 2023, with the title 'Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches'. Specifically, we consider domains in which there is implicit sequential information encapsulated in the data, e.g., in online bin-packing. We train two types of recurrent neural networks (RNN) to predict a packing heuristic in online bin-packing that use the sequence of item-sizes as input, i.e. no features are derived to describe the instance. This contrasts to typical approaches to algorithm-selection. 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. In order to explain the observed result, we suggest that our methods perform well when the instances exhibit some implicit structure. To provide evidence for this, 14 new datasets with controllable levels of structure are generated, indicating that a critical threshold of structure is required before algorithm-selection delivers benefit.
引用
收藏
页码:9 / 10
页数:2
相关论文
共 50 条
  • [31] A Deep Learning Approach with Feature Derivation and Selection for Overdue Repayment Forecasting
    Liu, Bin
    Zhang, Zhexi
    Yan, Junchi
    Zhang, Ning
    Zha, Hongyuan
    Li, Guofu
    Li, Yanting
    Yu, Quan
    APPLIED SCIENCES-BASEL, 2020, 10 (23): : 1 - 18
  • [32] A Watershed and Feature based approach for automated detection of lymphocytes on lung cancer images
    Corredor, German
    Wang, Xiangxue
    Lu, Cheng
    Velcheti, Vamsidhar
    Romero, Eduardo
    Madabhushi, Anant
    MEDICAL IMAGING 2018: DIGITAL PATHOLOGY, 2018, 10581
  • [33] Automated deep feature fusion based approach for the classification of multiclass rice diseases
    Nadide Yucel
    Muhammed Yildirim
    Iran Journal of Computer Science, 2024, 7 (1) : 131 - 138
  • [34] A Machine Learning Approach to Algorithm Selection for Exact Computation of Treewidth
    Slavchev, Borislav
    Masliankova, Evelina
    Kelk, Steven
    ALGORITHMS, 2019, 12 (10)
  • [35] Improving the Classification Performance of Asphalt Cracks After Earthquake With a New Feature Selection Algorithm
    Yilmaz, Mehmet
    Yalcin, Erkut
    Kifah, Saif
    Demir, Fatih
    Sengur, Abdulkadir
    Demir, Rozerin
    Mehmood, Raja Majid
    IEEE ACCESS, 2024, 12 (6604-6614) : 6604 - 6614
  • [36] Chaotic Dingo Optimization Algorithm: Application in Feature Selection for Beamforming Aided Spectrum Sensing
    Ben Chaabane, Sarra
    Bouallegue, Kais
    Belazi, Akram
    Kharbech, Sofiane
    Bouallegue, Ammar
    COMPUTATIONAL COLLECTIVE INTELLIGENCE, ICCCI 2022, 2022, 13501 : 660 - 673
  • [37] Categorizing the Students' Activities for Automated Exam Proctoring Using Proposed Deep L2-GraftNet CNN Network and ASO Based Feature Selection Approach
    Saba, Tanzila
    Rehman, Amjad
    Jamail, Nor Shahida Mohd
    Marie-Sainte, Souad Larabi
    Raza, Mudassar
    Sharif, Muhammad
    IEEE ACCESS, 2021, 9 : 47639 - 47656
  • [38] Automated Detection of Myocardial Infarction and Heart Conduction Disorders Based on Feature Selection and a Deep Learning Model
    Hammad, Mohamed
    Chelloug, Samia Allaoua
    Alkanhel, Reem
    Prakash, Allam Jaya
    Muthanna, Ammar
    Elgendy, Ibrahim A.
    Plawiak, Pawel
    SENSORS, 2022, 22 (17)
  • [39] ICA based Feature Learning and Feature Selection
    Ibrahim, Marwa Farouk Ibrahim
    Al-Jumaily, Adel Ali
    2016 5TH INTERNATIONAL CONFERENCE ON ELECTRONIC DEVICES, SYSTEMS AND APPLICATIONS (ICEDSA), 2016,
  • [40] Feature Selection in Pre-Diagnosis Heart Coronary Artery Disease Detection A heuristic approach for feature selection based on Information Gain Ratio and Gini Index
    Ghasemi, Foad
    Neysiani, Behzad Soleimani
    Nematbakhsh, Naser
    2020 6TH INTERNATIONAL CONFERENCE ON WEB RESEARCH (ICWR), 2020, : 27 - 32