Towards Efficient and Explainable Automated Machine Learning Pipelines Design

---

Authors

Moncef Garouani¹ , Mourad Bouneffa¹ , Adeel Ahmad¹

1. Univ. Littoral Côte d’Opale

Conference / event

International Conference on Artificial Intelligence and Big Data in Digital Era (ICABDE), December 2021 (Virtual)

Poster summary

The Machine Learning (ML) based data analytics solutions often require skilled resources. More practical non-expert software solutions are then desired to enhance the usability of ML algorithms. The algorithms selection and configuration is one of the most difficult tasks for non-experts users. The identification of the most appropriate algorithm in an automatic manner is among the major research challenges to achieve optimal performance of ML tools. In this poster, we present an auto-explained Automated Machine Learning tool to better cope with the prominent challenges posed by the evolution of Big Industrial Data. It is a meta-learning based decision support system for the automated selection and tuning of implied hyperparameters for ML algorithms. Moreover, the framework is equipped with an explainer module that makes the outcomes transparent and interpretable for well-performing ML systems.

Keywords

Automated machine learning, Meta-learning, Explainable AutoML, Decision-support systems

Research areas

Computer and Information Science

References

1. Garouani, M., Ahmad, A., Bouneffa., et al . Using meta learning for automated algorithms selection and configuration: an experimental framework for big industrial data. Journal of Big Data 9, 57 (2022). https://doi.org/10.1186/s40537-022-00612-4.
2. Garouani, M., Ahmad, A., Bouneffa, M, et al . Towards big industrial data mining through explainable automated machine learning. The International Journal of Advanced Manufacturing Technology (2022). https://doi.org/10.1007/s00170-022-08761-9.
3. Garouani, M., Ahmad, A., Bouneffa, M., et al AMLBID: An Automated Machine Learning tool for Big Industrial Data. SoftwareX (2021) 100919, https://doi.org/10.1016/j.softx.2021.100919.

Funding

No data provided

Supplemental files

No data provided

Additional information

Competing interests

None declared.

Data availability statement

The datasets generated during and/or analyzed during the current study are available from the corresponding author author on reasonable request.

Creative Commons license

Copyright © 2022 Garouani et al. This is an open access work distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.