Learning Qualitatively Diverse and Interpretable Rules for Classification
This addresses the need for explainable AI by providing diverse interpretable models, though it appears incremental as it builds on existing classification methods.
The paper tackles the problem of identifying multiple distinct but accurate models for classification when data supports them, demonstrating that their method tends to recover simpler and more interpretable classifiers.
There has been growing interest in developing accurate models that can also be explained to humans. Unfortunately, if there exist multiple distinct but accurate models for some dataset, current machine learning methods are unlikely to find them: standard techniques will likely recover a complex model that combines them. In this work, we introduce a way to identify a maximal set of distinct but accurate models for a dataset. We demonstrate empirically that, in situations where the data supports multiple accurate classifiers, we tend to recover simpler, more interpretable classifiers rather than more complex ones.