SIBILA: Automated Machine-Learning-Based Development of Interpretable Machine-Learning Models on High-Performance Computing Platforms
As machine learning (ML) transforms industries, the need for efficient model development tools using high-performance computing (HPC) and ensuring interpretability is crucial. This paper presents SIBILA, an AutoML approach designed for HPC environments, focusing on the interpretation of ML models. S...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/5/4/116 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850240587014340608 |
|---|---|
| author | Antonio Jesús Banegas-Luna Horacio Pérez-Sánchez |
| author_facet | Antonio Jesús Banegas-Luna Horacio Pérez-Sánchez |
| author_sort | Antonio Jesús Banegas-Luna |
| collection | DOAJ |
| description | As machine learning (ML) transforms industries, the need for efficient model development tools using high-performance computing (HPC) and ensuring interpretability is crucial. This paper presents SIBILA, an AutoML approach designed for HPC environments, focusing on the interpretation of ML models. SIBILA simplifies model development by allowing users to set objectives and preferences before automating the search for optimal ML pipelines. Unlike traditional AutoML frameworks, SIBILA is specifically designed to exploit the computational capabilities of HPC platforms, thereby accelerating the model search and evaluation phases. The emphasis on interpretability is particularly crucial when model transparency is mandated by regulations or desired for stakeholder understanding. SIBILA has been validated in different tasks with public datasets. The results demonstrate that SIBILA consistently produces models with competitive accuracy while significantly reducing computational overhead. This makes it an ideal choice for practitioners seeking efficient and transparent ML solutions on HPC infrastructures. SIBILA is a major advancement in AutoML, addressing the rising demand for explainable ML models on HPC platforms. Its integration of interpretability constraints alongside automated model development processes marks a substantial step forward in bridging the gap between computational efficiency and model transparency in ML applications. The tool is available as a web service at no charge. |
| format | Article |
| id | doaj-art-9556da841e034e9faee990c181fc42dd |
| institution | OA Journals |
| issn | 2673-2688 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj-art-9556da841e034e9faee990c181fc42dd2025-08-20T02:00:50ZengMDPI AGAI2673-26882024-11-01542353237410.3390/ai5040116SIBILA: Automated Machine-Learning-Based Development of Interpretable Machine-Learning Models on High-Performance Computing PlatformsAntonio Jesús Banegas-Luna0Horacio Pérez-Sánchez1Structural Bioinformatics and High-Performance Computing (BIO-HPC), Campus de los Jerónimos, Universidad Católica de Murcia (UCAM), Guadalupe, 30107 Murcia, SpainStructural Bioinformatics and High-Performance Computing (BIO-HPC), Campus de los Jerónimos, Universidad Católica de Murcia (UCAM), Guadalupe, 30107 Murcia, SpainAs machine learning (ML) transforms industries, the need for efficient model development tools using high-performance computing (HPC) and ensuring interpretability is crucial. This paper presents SIBILA, an AutoML approach designed for HPC environments, focusing on the interpretation of ML models. SIBILA simplifies model development by allowing users to set objectives and preferences before automating the search for optimal ML pipelines. Unlike traditional AutoML frameworks, SIBILA is specifically designed to exploit the computational capabilities of HPC platforms, thereby accelerating the model search and evaluation phases. The emphasis on interpretability is particularly crucial when model transparency is mandated by regulations or desired for stakeholder understanding. SIBILA has been validated in different tasks with public datasets. The results demonstrate that SIBILA consistently produces models with competitive accuracy while significantly reducing computational overhead. This makes it an ideal choice for practitioners seeking efficient and transparent ML solutions on HPC infrastructures. SIBILA is a major advancement in AutoML, addressing the rising demand for explainable ML models on HPC platforms. Its integration of interpretability constraints alongside automated model development processes marks a substantial step forward in bridging the gap between computational efficiency and model transparency in ML applications. The tool is available as a web service at no charge.https://www.mdpi.com/2673-2688/5/4/116explainable machine learningdata fusionautomated machine learninghigh-performance computingdeep learningconsensus |
| spellingShingle | Antonio Jesús Banegas-Luna Horacio Pérez-Sánchez SIBILA: Automated Machine-Learning-Based Development of Interpretable Machine-Learning Models on High-Performance Computing Platforms AI explainable machine learning data fusion automated machine learning high-performance computing deep learning consensus |
| title | SIBILA: Automated Machine-Learning-Based Development of Interpretable Machine-Learning Models on High-Performance Computing Platforms |
| title_full | SIBILA: Automated Machine-Learning-Based Development of Interpretable Machine-Learning Models on High-Performance Computing Platforms |
| title_fullStr | SIBILA: Automated Machine-Learning-Based Development of Interpretable Machine-Learning Models on High-Performance Computing Platforms |
| title_full_unstemmed | SIBILA: Automated Machine-Learning-Based Development of Interpretable Machine-Learning Models on High-Performance Computing Platforms |
| title_short | SIBILA: Automated Machine-Learning-Based Development of Interpretable Machine-Learning Models on High-Performance Computing Platforms |
| title_sort | sibila automated machine learning based development of interpretable machine learning models on high performance computing platforms |
| topic | explainable machine learning data fusion automated machine learning high-performance computing deep learning consensus |
| url | https://www.mdpi.com/2673-2688/5/4/116 |
| work_keys_str_mv | AT antoniojesusbanegasluna sibilaautomatedmachinelearningbaseddevelopmentofinterpretablemachinelearningmodelsonhighperformancecomputingplatforms AT horacioperezsanchez sibilaautomatedmachinelearningbaseddevelopmentofinterpretablemachinelearningmodelsonhighperformancecomputingplatforms |