FSPL: A Meta–Learning Approach for a Filter and Embedded Feature Selection Pipeline
There are two main approaches to tackle the challenge of finding the best filter or embedded feature selection (FS) algorithm: searching for the one best FS algorithm and creating an ensemble of all available FS algorithms. However, in practice, these two processes usually occur as part of a larger...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2023-03-01
|
| Series: | International Journal of Applied Mathematics and Computer Science |
| Subjects: | |
| Online Access: | https://doi.org/10.34768/amcs-2023-0009 |
| _version_ | 1797848534520692736 |
|---|---|
| author | Lazebnik Teddy Rosenfeld Avi |
| author_facet | Lazebnik Teddy Rosenfeld Avi |
| author_sort | Lazebnik Teddy |
| collection | DOAJ |
| description | There are two main approaches to tackle the challenge of finding the best filter or embedded feature selection (FS) algorithm: searching for the one best FS algorithm and creating an ensemble of all available FS algorithms. However, in practice, these two processes usually occur as part of a larger machine learning pipeline and not separately. We posit that, due to the influence of the filter FS on the embedded FS, one should aim to optimize both of them as a single FS pipeline rather than separately. We propose a meta-learning approach that automatically finds the best filter and embedded FS pipeline for a given dataset called FSPL. We demonstrate the performance of FSPL on n = 90 datasets, obtaining 0.496 accuracy for the optimal FS pipeline, revealing an improvement of up to 5.98 percent in the model’s accuracy compared to the second-best meta-learning method. |
| first_indexed | 2024-04-09T18:29:06Z |
| format | Article |
| id | doaj.art-d2e5ae146df94e4bbb5c0b13550d6019 |
| institution | Directory Open Access Journal |
| issn | 2083-8492 |
| language | English |
| last_indexed | 2024-04-09T18:29:06Z |
| publishDate | 2023-03-01 |
| publisher | Sciendo |
| record_format | Article |
| series | International Journal of Applied Mathematics and Computer Science |
| spelling | doaj.art-d2e5ae146df94e4bbb5c0b13550d60192023-04-11T17:28:19ZengSciendoInternational Journal of Applied Mathematics and Computer Science2083-84922023-03-0133110311510.34768/amcs-2023-0009FSPL: A Meta–Learning Approach for a Filter and Embedded Feature Selection PipelineLazebnik Teddy0Rosenfeld Avi11Department of Cancer Biology, University College London Cancer Institute, 72 Huntley St., WC1E 6DD, London, UK2Department of Computer Science, Jerusalem College of Technology, 21 Ha-Va’ad ha-Le’umi St., Jerusalem, IsraelThere are two main approaches to tackle the challenge of finding the best filter or embedded feature selection (FS) algorithm: searching for the one best FS algorithm and creating an ensemble of all available FS algorithms. However, in practice, these two processes usually occur as part of a larger machine learning pipeline and not separately. We posit that, due to the influence of the filter FS on the embedded FS, one should aim to optimize both of them as a single FS pipeline rather than separately. We propose a meta-learning approach that automatically finds the best filter and embedded FS pipeline for a given dataset called FSPL. We demonstrate the performance of FSPL on n = 90 datasets, obtaining 0.496 accuracy for the optimal FS pipeline, revealing an improvement of up to 5.98 percent in the model’s accuracy compared to the second-best meta-learning method.https://doi.org/10.34768/amcs-2023-0009feature selection pipelinemeta-learningno free lunchautomlgenetic algorithm |
| spellingShingle | Lazebnik Teddy Rosenfeld Avi FSPL: A Meta–Learning Approach for a Filter and Embedded Feature Selection Pipeline International Journal of Applied Mathematics and Computer Science feature selection pipeline meta-learning no free lunch automl genetic algorithm |
| title | FSPL: A Meta–Learning Approach for a Filter and Embedded Feature Selection Pipeline |
| title_full | FSPL: A Meta–Learning Approach for a Filter and Embedded Feature Selection Pipeline |
| title_fullStr | FSPL: A Meta–Learning Approach for a Filter and Embedded Feature Selection Pipeline |
| title_full_unstemmed | FSPL: A Meta–Learning Approach for a Filter and Embedded Feature Selection Pipeline |
| title_short | FSPL: A Meta–Learning Approach for a Filter and Embedded Feature Selection Pipeline |
| title_sort | fspl a meta learning approach for a filter and embedded feature selection pipeline |
| topic | feature selection pipeline meta-learning no free lunch automl genetic algorithm |
| url | https://doi.org/10.34768/amcs-2023-0009 |
| work_keys_str_mv | AT lazebnikteddy fsplametalearningapproachforafilterandembeddedfeatureselectionpipeline AT rosenfeldavi fsplametalearningapproachforafilterandembeddedfeatureselectionpipeline |