Interpretable Decision Sets: A Joint Framework for Description and Prediction

By Himabindu Lakkaraju, Stephen H. Bach, Jure Leskovec. 2016

865 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

Citations in the corpus

Measuring Progress on Scalable Oversight for Large Language Models (2022, background): “…with the literature on human–AI team decision making, surveyed in Lai et al. (2021), and including targeted case studies on recidivism prediction (e.g. Liu et al., 2021), medical diagnosis (e.g. Lakkaraju et al., 2016), and credit risk prediction (e.g. Chromik et al., 2021), among many others.”
Towards A Rigorous Science of Interpretable Machine Learning (2017, background): “…time constraints, one might create abstract tasks in which other factors—such as the overall task complexity—can be controlled [Kim et al., 2013, Lakkaraju et al., 2016] The key question, of course, is how we can evaluate the quality of an explanation without a speciﬁc end-goal (such as…”
Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “…lists (Rudin and Ertekin, 2016; Yu et al., 2020a; Angelino et al., 2017, 2018; Aı̈vodji et al., 2019) and decision sets (Wang and Rudin, 2015b; Lakkaraju et al., 2016; Ignatiev et al., 2018; Dash et al., 2018b; Malioutov and Meel, 2018; Ghosh and Meel, 2019; Dhamnani et al., 2019; Yu et…”
Learning Optimal Decision Trees with SAT (2018, methodology): “This is the case with decision trees [ Bessiere et al. , 2009 ] , but also with rule lists and rule sets [Lakkaraju et al. , 2016; Angelino et al. , 2017].”
Local Rule-Based Explanations of Black Box Decision Systems (2018, background): “In the cases in which the training set is available, classification rules are also widely used to avoid building black boxes by directly designing a transparent classifier [17] which is locally or globally interpretable on its own [23, 25, 39].”
Anchors: High-Precision Model-Agnostic Explanations (2018, background): “…machine learning has seen a resurgence in recent years, ranging from the design of novel globally-interpretable machine learning models (Lakkaraju, Bach, and Leskovec 2016; Ustun and Rudin 2015; Wang and Rudin 2015) to local explanations (for individual predictions) that can be…”
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability (2017, background): “…research efforts have emphasized that simple lists of (perhaps locally) important features are not sufﬁcient: Singh, Ribeiro, and Guestrin (2016) provide explanations in the form of programs; Lakkaraju, Bach, and Leskovec (2016) learn decision sets and show beneﬁts over other rule-based methods.”
Challenges for Transparency (2017, background): “Lakkaraju et al. (2016) introduced measures of human interpretability based on being able to describe a decision boundary, which would facilitate model reconstruction.”
Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making (2019, methodology): “Finally our work relates to interpretable ML, including works on decision rules (Wang et al. 2017; Letham et al. 2015), decision sets (Lakkaraju, Bach, and Jure 2016), and generalized additive models (Lou et al. 2013a).”
How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning (2021, methodology): “Model Frequency range [0, 10]kHz [10, 20]kHz [20, 30]kHz [30, 40]kHz [40, 50]kHz”
Predictive Multiplicity in Classification (2019, background): “4These are rule-based models that can be expressed as special kinds of linear classifiers, such as decision sets [28], decision lists [3], or and-of-or rules [51].”