SustainaML: Enhancing Transparency, Control, and Green Sustainability in AutoML

Abstract

Automated machine learning (AutoML) enhances accessibility but often suffers from a lack of transparency and user control due to its complex and opaque processes. We introduce SustainaML, a lightweight visualization interface built atop FLAML, H2O, and MLJAR, enabling interactive refinement of AutoML search spaces and evaluation based on both performance and sustainability metrics. SustainaML offers flexible configurations and actionable visual feedback. A user study comparing SustainaML with ATMSeer demonstrates superior usability and effectiveness in promoting transparent, resource-efficient AutoML workflows.

Cite

Text

Malik and El Shawi. "SustainaML: Enhancing Transparency, Control, and Green Sustainability in AutoML." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025. doi:10.1007/978-3-032-06129-4_30

Markdown

[Malik and El Shawi. "SustainaML: Enhancing Transparency, Control, and Green Sustainability in AutoML." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025.](https://mlanthology.org/ecmlpkdd/2025/malik2025ecmlpkdd-sustainaml/) doi:10.1007/978-3-032-06129-4_30

BibTeX

@inproceedings{malik2025ecmlpkdd-sustainaml,
  title     = {{SustainaML: Enhancing Transparency, Control, and Green Sustainability in AutoML}},
  author    = {Malik, Mehak Mushtaq and El Shawi, Radwa},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2025},
  pages     = {454-459},
  doi       = {10.1007/978-3-032-06129-4_30},
  url       = {https://mlanthology.org/ecmlpkdd/2025/malik2025ecmlpkdd-sustainaml/}
}