Visualizing Rule Sets: Exploration and Validation of a Design Space
This work addresses the problem of improving transparency and intelligibility in ML for practitioners, though it is incremental as it builds on existing rule-based communication methods.
The paper tackled the lack of visual alternatives for presenting rule sets in machine learning by exploring a design space for visualizing them, finding that certain visual factors significantly improve processing efficiency with minimal accuracy loss.
Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logical statements (rules). Surprisingly, to date there has been limited work on exploring visual alternatives for presenting rules. In this paper, we explore the idea of designing alternative representations of rules, focusing on a number of visual factors we believe have a positive impact on rule readability and understanding. The paper presents an initial design space for visualizing rule sets and a user study exploring their impact. The results show that some design factors have a strong impact on how efficiently readers can process the rules while having minimal impact on accuracy. This work can help practitioners employ more effective solutions when using rules as a communication strategy to understand ML models.