Embedded Constrained Feature Construction for High-Energy Physics Data Classification
This work addresses the problem of interpretability and performance for physicists validating data in high-energy physics experiments, though it is incremental as it builds on existing feature construction methods.
The paper tackles the need for transparent machine learning in high-energy physics by embedding feature construction within tree-based models, resulting in significant gains in classification scores while limiting feature count.
Before any publication, data analysis of high-energy physics experiments must be validated. This validation is granted only if a perfect understanding of the data and the analysis process is demonstrated. Therefore, physicists prefer using transparent machine learning algorithms whose performances highly rely on the suitability of the provided input features. To transform the feature space, feature construction aims at automatically generating new relevant features. Whereas most of previous works in this area perform the feature construction prior to the model training, we propose here a general framework to embed a feature construction technique adapted to the constraints of high-energy physics in the induction of tree-based models. Experiments on two high-energy physics datasets confirm that a significant gain is obtained on the classification scores, while limiting the number of built features. Since the features are built to be interpretable, the whole model is transparent and readable.