Unsupervised Approach for Learning Behavioral Constraints

Constrained machine learning (ML) models consists of incorporating a set of constraints into the ML model. The latter is generally used to incorporate domain knowledge, enhance performance, and define fair and robust ML models. Several papers reported that defining a full set of constraints is challenging. To address this issue, approaches for learning constraints were proposed. These approaches established general rules governing the data and dismissed any sample-related information. However, in user profiling tasks it is important to understand the position of each individual. In this paper, we define behavioral constraints as the set of numerical values that reflect the characteristics of each individual in the dataset. We propose an unsupervised approach for learning these behavioral constraints (ULBC). Applied to two datasets, the approach effectively provided behavioral constraints that unravel the similarities and dissimilarities between individuals.