AutoML: Examining Existing Software Implementations and Determining the Overall Internal Structure of Solutions

Cover Page

Cite item

Full Text

Abstract

The article discusses various software implementations of the process of automating the task of using machine learning to solve the linear regression problem. The internal structure and capabilities of a number of existing and widely used automated machine learning tools such as LightAutoML (LAMA), TPOT, AutoSklearn, H2O AutoML, MLJAR are considered. The capabilities of these software systems have been explored to solve the regression problem on multiple datasets.

About the authors

Inna A. Popova

Bauman Moscow State Technical University

Email: popovai1@student.bmstu.ru

Graduate student

Russian Federation, 2-nd Baumanskaya, 5, Moscow, 105005

Yuriy E. Gapanyuk

Bauman Moscow State Technical University

Author for correspondence.
Email: gapyu@bmstu.ru

Associate professor

Russian Federation, 2-nd Baumanskaya, 5, Moscow, 105005

Georgiy I. Revunkov

Bauman Moscow State Technical University

Email: revunkov@bmstu.ru

Associate professor

Russian Federation, 2-nd Baumanskaya, 5, Moscow, 105005

References

  1. Nagarajah, T., Poravi, G. A Review on Automated Machine Learning (AutoML) Systems. In: 2019 IEEE 5th International Conference for Convergence in Technology (I2CT), pp. 1–6. Pune, India (2019). https://doi.org/10.1109/I2CT45611.2019.9033810
  2. Bahri, M., Salutari, F., Putina, A. et al. AutoML: state of the art with a focus on anomaly detection, challenges, and research directions. Int J Data Sci Anal (2022). https://doi.org/10.1007/s41060-022-00309-0
  3. Karmaker, S., Hassan, M.M., Smith, M.J., Xu, L., Zhai, C., Veeramachaneni, K. AutoML to Date and Beyond: Challenges and Opportunities. ACM Computing Surveys (CSUR) 54, 1–36 (2022)
  4. He X., Zhao K., Chu X. AutoML: A survey of the state-of-the-art. Knowl. Based Syst., 212, 106622. https://doi.org/10.1016/j.knosys.2020.106622
  5. Escalante, H.J. Automated Machine Learning – a brief review at the end of the early years. arXiv:2008.08516. https://doi.org/10.48550/ arXiv.2008.08516
  6. Bahri, M., Salutari, F., Putina, A., Sozio, M. AutoML: state of the art with a focus on anomaly detection, challenges, and research directions. International Journal of Data Science and Analytics, Springer Verlag, 2022. https://doi. org/10.1007/s41060-022-00309-0
  7. Koroteev, M.V. Review of some modern trends in machine learning technology. E-Management 1(1), 26–35 (2018)
  8. Feurer, M., Eggensperger, K., Falkner, S., Lindauer, M.T., Hutter, F. Practical Automated Machine Learning for the AutoML Challenge 2018. In: International Workshop on Automatic Machine Learning at ICML, pp. 1189-1232 (2018)
  9. Car Dekho Data, https://www.kaggle.com/ datasets/shindenikhil/car-dekho-data. Last accessed 12 December 2022
  10. Combined Cycle Power Plant Dataset, https:// archive.ics.uci.edu/ ml/ datasets/ Combined+Cycle+Power+Plant. Last accessed 12 December 2022
  11. LightAutoML – Automatic model creation framework, https://github.com/sb-ailab/ LightAutoML. Last accessed 12 December 2022
  12. TPOT – A Python Automated Machine Learning tool, https://github.com/EpistasisLab/tpot. Last accessed 12 December 2022
  13. Auto-Sklearn – An automated machine learning toolkit, https://github.com/automl/auto-sklearn. Last accessed 12 December 2022
  14. H2O AutoML – Open-Source Automated Machine Learning, https://h2o.ai/platform/h2o-automl/. Last accessed 12 December 2022
  15. MLJAR – Automate your Machine Learning pipeline, https://mljar.com/. Last accessed 12 December 2022
  16. Chen, Yi-Wei, Qingquan Song, and Xia Hu.: Techniques for automated machine learning. ACM SIGKDD Explorations Newsletter, 35-50 (2021).
  17. Elshawi, Radwa, Mohamed Maher, and Sherif Sakr: Automated machine learning: State-ofthe-art and open challenges. arXiv preprint arXiv:1906.02287 (2019).
  18. Vakhrushev, Anton, et al. LightAutoML: AutoML Solution for a Large Financial Services Ecosystem. arXiv preprint arXiv:2109.01528 (2021).

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).