Semantic Feature Discovery with Code Mining and Semantic Type Detection


  • Kavitha Srinivas IBM Research
  • Takaaki Tateishi IBM Research
  • Daniel Karl I. Weidele IBM Research
  • Udayan Khurana IBM Research
  • Horst Samulowitz IBM Research
  • Toshihiro Takahashi IBM Research
  • Dakuo Wang IBM Research
  • Lisa Amini IBM Research



Semantic Feature Discovery, Automated Machine Learning, Automl, Semantic Web, Code Mining


In recent years, the automation of machine learning and data science (AutoML) has attracted significant attention. One under-explored dimension of AutoML is being able to automatically utilize domain knowledge (such as semantic concepts and relationships) located in historical code or literature from the problem's domain. In this paper, we demonstrate Semantic Feature Discovery, which enables users to interactively explore features semantically discovered from existing data science code and external knowledge. It does so by detecting semantic concepts for a given dataset, and then using these concepts to determine relevant feature engineering operations from historical code and knowledge.




How to Cite

Srinivas, K., Tateishi, T., Weidele, D. K. I., Khurana, U., Samulowitz, H., Takahashi, T., Wang, D., & Amini, L. (2022). Semantic Feature Discovery with Code Mining and Semantic Type Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 13224-13226.