CoChat
Sign Up
Cited by 687Explainable Artificial Intelligence (XAI)Data Mining Algorithms and ApplicationsMachine Learning and Data Classification

Interpretable Decision Sets: A Joint Framework for Description and Prediction

Open access
Lakkaraju, Himabindu, Bach, Stephen H., Leskovec, Jure·2016·Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
DOI 10.1145/2939672.2939874PMC PMC5108651
Open this paper in CoChat — free account

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.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/2939672.2939874

Cites

59 of 59 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • As users of ML systems have grown beyond ML experts and the research community, the need to better interpret and understand them has grown, particularly in high-stakes decisions that affect individuals' health or wellbeing.

    “As users of these systems have grown beyond ML experts and the research community, the need to better interpret and understand them has grown as well, particularly in the context of high-stakes decisions that affect individuals ' health or wellbeing (Lakkaraju et al., 2016; Lipton, 2018; Rudin, 2019).”

    From Explainable machine learning for public policy: Use cases, gaps, and research directions (2023) · cites this paper as Lakkaraju et al., 2016

  • Inherently interpretable ML models are designed such that an end user could understand their decision-making process.

    “Inherently interpretable ML models are designed such that an end user could understand its decisionmaking process (Lakkaraju et al., 2016; Rudin, 2019).”

    From Explainable machine learning for public policy: Use cases, gaps, and research directions (2023) · cites this paper as Lakkaraju et al., 2016

  • Interpretable models often rely on carefully curated representations of data with meaningful input features, often through discretization or binary encoding.

    “Interpretable models often rely on carefully curated representations of data with meaningful input features (Rudin, 2019), often through discretization or binary encoding (Caruana et al., 2015; Lakkaraju et al., 2016; Ustun and Rudin, 2019).”

    From Explainable machine learning for public policy: Use cases, gaps, and research directions (2023) · cites this paper as Lakkaraju et al., 2016

    The citation to Lakkaraju et al. is attached to the claim about discretization or binary encoding. Section 3.1 defines rules using predicates on input attributes, including a numerical threshold, but does not say that the input features are discretized or binary-encoded. Searches for those preprocessing steps found no supporting passage; the binarization mentioned in §5.1 concerns class labels for calculating AUC, not input features. (LLM, conf=0.73)

    Experimental — accuracy not yet measured

  • Some papers already optimize for interpretability by using a regularization term or objective function during training of the predictive model or by relating rewards to explainability and presentation quality in reinforcement learning.

    “Some papers already optimize for interpretability by using a regularization term or objective function during training of the predictive model (e.g., [33,137,191,211,244,276,277,289]) or by relating rewards to explainability and presentation quality in reinforcement learning (e.g., [268]).”

    From From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2023) · cites this paper as [137]

  • Rule-based methods are advantageous because they are interpretable.

    “rule-based methods have the advantage of interpretability [2,51,55,60,61].”

    From Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making (2023) · cites this paper as [55]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. [32]Lakkaraju H Bach SH Leskovec J Interpretable decision sets: A joint framework for description and prediction Technical report, Stanford InfoLab 2016 PMC5108651 27853627

Cited by

Sorted by citations

Related

Authors
Lakkaraju, H., Bach, S. H., & Leskovec, J.
Affiliations
Stanford University (US)
ORCID
Venue
Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Publisher
ACM
Published
2016-08-13
Volume
2016
Pages
1675-1684
DOI
10.1145/2939672.2939874
PMC
PMC5108651
OpenAlex
W2367397349
Cited by
687
References
59
Citations by year
2026: 33 · 2025: 51 · 2024: 58 · 2023: 83 · 2022: 69 · 2021: 106 · 2020: 104 · 2019: 102 · 2018: 51 · 2017: 22 · 2016: 8
FWCI
32.25
Type
conference paper
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
  • ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
Funders
  • National Institutes of Health
  • National Institute of Biomedical Imaging and Bioengineering (U54EB020405)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
Keywords
if-then rules, rule-based models, model interpretability, submodular optimization, non-monotone submodular functions, accuracy-interpretability trade-off, decision boundaries, user study

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review