Physics-constrained Automatic Feature Engineering for Predictive Modeling in Materials Science Conference Paper uri icon

abstract

  • Automatic Feature Engineering (AFE) aims to extract useful knowledge for interpretable predictions given data for the machine learning tasks. Here, we develop AFE to extract dependency relationships that can be interpreted with functional formulas to discover physics meaning or new hypotheses for the problems of interest. We focus on materials science applications, where interpretable predictive modeling may provide principled understanding of materials systems and guide new materials discovery. It is often computationally prohibitive to exhaust all the potential relationships to construct and search the whole feature space to identify interpretable and predictive features. We develop and evaluate new AFE strategies by exploring a feature generation tree (FGT) with deep Q-network (DQN) for scalable and efficient exploration policies. The developed DQN-based AFE strategies are benchmarked with the existing AFE methods on several materials science datasets.

published proceedings

  • THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

author list (cited authors)

  • Xiang, Z., Fan, M., Tovar, G. V., Trehem, W., Yoon, B., Qian, X., Arroyave, R., & Qian, X.

citation count

  • 5

complete list of authors

  • Xiang, Ziyu||Fan, Mingzhou||Tovar, Guillermo Vazquez||Trehem, William||Yoon, Byung-Jun||Qian, Xiaofeng||Arroyave, Raymundo||Qian, Xiaoning

publication date

  • January 2021