Interpretable Decision Sets

Abstract

One of the most important obstacles to deploying predictive models is the fact that humans do not understand and trust them. Knowing which variables are important in a model’s prediction and how they are combined can be very powerful in helping people understand and trust automatic decision making systems. Here we propose interpretable decision sets, a framework for building predictive models that are highly accurate, yet also highly interpretable. Decision sets are sets of independent if-then rules. Because each rule can be applied independently, decision sets are simple, concise, and easily interpretable. We formalize decision set learning through an objective function that simultaneously optimizes accuracy and interpretability of the rules. In particular, our approach learns short, accurate, and non-overlapping rules that cover the whole feature space and pay attention to small but important classes. Moreover, we prove that our objective is a non-monotone submodular function, which we efficiently optimize to find a near-optimal set of rules. Experiments show that interpretable decision sets are as accurate at classification as state-of-the-art machine learning techniques. They are also three times smaller on average than rule-based models learned by other methods. Finally, results of a user study show that people are able to answer multiple-choice questions about the decision boundaries of interpretable decision sets and write descriptions of classes based on them faster and more accurately than with other rule-based models that were designed for interpretability. Overall, our framework provides a new approach to interpretable machine learning that balances accuracy, interpretability, and computational efficiency.

Molecular networks in Network Medicine: Development and applications

“…Finally, it is important to mention the fact that many advanced ML approaches work as "black boxes," hiding the importance and the correlation of a set of features from the outcome (i.e., its biological interpretation), thus hindering the deployment of predictive models because ultimately, humans do not understand-nor trust-them (Camacho, Collins, Powers, Costello, & Collins, 2018). To overcome this issue, several efforts are being pursued in providing interpretable ML approaches able to balance interpretability, accuracy, and computational viability (Lakkaraju, Bach, & Leskovec, 2016;M. K. Yu et al, 2018).…”

Decision-Tree, Rule-Based, and Random Forest Classification of High-Resolution Multispectral Imagery for Wetland Mapping and Inventory

“…The DT developed in 2.7.2 (including the boosting conducted in Tests 10, 12, 14, and 16) was transformed into a simpler set of “if-then” rules in C5.0 by creating “rulesets” in the algorithm. The ruleset generated from the DT has fewer rules than the number of leaves in the decision tree, thus it is a more compact and simpler representation [ 88 ]. Since each conditional logic rule describes a specific context associated with a class, it is relatively easy to examine, validate, and interpret the ruleset.…”

Human-Machine Collaboration for Content Regulation

“…While the accuracy of such tools has risen for many kinds of moderation tasks, the tools often cannot explain their decisions, which makes mixed-initiative human-machine solutions challenging to design. Human-understandable ML is an active area of research [64]. Yet, as we will see, Automod does not rely on ML techniques but it rather uses simple rules and regularexpression matching, which can be understood by technically savvy human moderators.…”