VINE: Visualizing Statistical Interactions in Black Box Models
This addresses the need for interpretable explanations in mission-critical and socially aligned machine learning models, though it appears incremental by focusing on a specific gap in existing visualization methods.
The paper tackles the problem of visualizing statistical feature interactions and regional explanations in black box models, presenting VINE as a novel algorithm for this purpose and introducing a new evaluation metric for interpretable ML visualizations.
As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local (instance-specific) explanations. However, relatively little work has addressed regional explanations - how groups of similar instances behave in a complex model, and the related issue of visualizing statistical feature interactions. The lack of utilities available for these analytical needs hinders the development of models that are mission-critical, transparent, and align with social goals. We present VINE (Visual INteraction Effects), a novel algorithm to extract and visualize statistical interaction effects in black box models. We also present a novel evaluation metric for visualizations in the interpretable ML space.