A SAT-Based Approach to Learn Explainable Decision Sets

Ignatiev, Alexey; Pereira, Filipe; Narodytska, Nina; Marques-Silva, João

doi:10.1007/978-3-319-94205-6_41

Cited by 39 publications

(56 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sometimes decision lists or decision sets are optimized by sampling [180,321,306], providing a Bayesian interpretation. Some recent works can jointly optimize performance metrics and sparsity for decision lists [251,327,10,11,8] and decision sets [311,110,170,132,77,197,109,80,328,45]. Some works optimize for individual rules [77,255].…”

Section: Sparse Logical Models: Decision Trees Decision Lists Decision Setsmentioning

confidence: 99%

Interpretable machine learning: Fundamental principles and 10 grand challenges

Rudin¹,

Chen²,

Chen³

et al. 2022

Statist. Surv.

436

202

View full text Add to dashboard Cite

Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic. We also identify 10 technical challenge areas in interpretable machine learning and provide history and background on each problem. Some of these problems are classically important, and some are recent problems that have arisen in the last few years. These problems are: (1) Optimizing sparse logical models such as decision trees;(2) Optimization of scoring systems; (3) Placing constraints into generalized additive models to encourage sparsity and better interpretability; (4) Modern case-based reasoning, including neural networks and matching for causal inference; (5) Complete supervised disentanglement of neural networks; (6) Complete or even partial unsupervised disentanglement of neural networks; (7) Dimensionality reduction for data visualization; (8) Machine learning models that can incorporate physics and other generative or causal constraints; (9) Characterization of the "Rashomon set" of good models; and (10) Interpretable reinforcement learning. This survey is suitable as a starting point for statisticians and computer scientists interested in working in interpretable machine learning.

show abstract

Section: Sparse Logical Models: Decision Trees Decision Lists Decision Setsmentioning

confidence: 99%

Interpretable machine learning: Fundamental principles and 10 grand challenges

Rudin¹,

Chen²,

Chen³

et al. 2022

Statist. Surv.

436

202

View full text Add to dashboard Cite

show abstract

“…For example, decision sets [32] represent one such example of multi-class classification, where each function κ j is represented by a DNF, and a default rule is used to pick some class for the points v in feature space for which all κ j (v) = 0. Moreover, decision sets may exhibit overlap [29], i.e. the existence of points v in feature space such that there exist j 1 ̸ = j 2 and κ j1 (v) = κ j2 (v) = 1.…”

Section: Explanations For Generalized Decision Functionsmentioning

confidence: 99%

Efficient Explanations for Knowledge Compilation Languages

Huang,

Izza,

Ignatiev

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Knowledge compilation (KC) languages find a growing number of practical uses, including in Constraint Programming (CP) and in Machine Learning (ML). In most applications, one natural question is how to explain the decisions made by models represented by a KC language. This paper shows that for many of the best known KC languages, well-known classes of explanations can be computed in polynomial time. These classes include deterministic decomposable negation normal form (d-DNNF), and so any KC language that is strictly less succinct than d-DNNF. Furthermore, the paper also investigates the conditions under which polynomial time computation of explanations can be extended to KC languages more succinct than d-DNNF.

show abstract

“…Originally, IDS [11] specified to use the Smooth Local Search (SLS) algorithm [4]. However, as using SLS with IDS can be prohibitively slow [8], we choose to use the more recent Randomized Double Greedy Search algorithm [3], which is considerably faster and has better theoretical guarantees.…”

Section: Ids: (Single-target) Interpretable Decision Setsmentioning

confidence: 99%

Multi-directional Rule Set Learning

2020

View full text Add to dashboard Cite

A rule set is a type of classifier that, given attributes X, predicts a target Y. Its main advantage over other types of classifiers is its simplicity and interpretability. A practical challenge is that the end user of a rule set does not always know in advance which target will need to be predicted. One way to deal with this is to learn a multi-directional rule set, which can predict any attribute from all others. An individual rule in such a multi-directional rule set can have multiple targets in its head, and thus be used to predict any one of these. Compared to the naive approach of learning one rule set for each possible target and merging them, a multi-directional rule set containing multi-target rules is potentially smaller and more interpretable. Training a multi-directional rule set involves two key steps: generating candidate rules and selecting rules. However, the best way to tackle these steps remains an open question. In this paper, we investigate the effect of using Random Forests as candidate rule generators and propose two new approaches for selecting rules with multi-target heads: MIDS, a generalization of the recent single-target IDS approach, and RR, a new simple algorithm focusing only on predictive performance. Our experiments indicate that (1) using multi-target rules leads to smaller rule sets with a similar predictive performance, (2) using Forest-derived rules instead of association rules leads to rule sets of similar quality, and (3) RR outperforms MIDS, underlining the usefulness of simple selection objectives.

show abstract

A SAT-Based Approach to Learn Explainable Decision Sets

Cited by 39 publications

References 23 publications

Interpretable machine learning: Fundamental principles and 10 grand challenges

Interpretable machine learning: Fundamental principles and 10 grand challenges

Efficient Explanations for Knowledge Compilation Languages

Multi-directional Rule Set Learning

Contact Info

Product

Resources

About