Efficient learning of large sets of locally optimal classification rules
From MaRDI portal
Abstract: Conventional rule learning algorithms aim at finding a set of simple rules, where each rule covers as many examples as possible. In this paper, we argue that the rules found in this way may not be the optimal explanations for each of the examples they cover. Instead, we propose an efficient algorithm that aims at finding the best rule covering each training example in a greedy optimization consisting of one specialization and one generalization loop. These locally optimal rules are collected and then filtered for a final rule set, which is much larger than the sets learned by conventional rule learning algorithms. A new example is classified by selecting the best among the rules that cover this example. In our experiments on small to very large datasets, the approach's average classification accuracy is higher than that of state-of-the-art rule learning algorithms. Moreover, the algorithm is highly efficient and can inherently be processed in parallel without affecting the learned rule set and so the classification accuracy. We thus believe that it closes an important gap for large-scale classification rule induction.
Recommendations
Cites work
- A Bayesian framework for learning rule sets for interpretable classification
- A new algorithm for fast mining frequent itemsets using N-lists
- Branch-and-price: Column generation for solving huge integer programs
- Foundations of Rule Learning
- FUSINTER: A Method for Discretization of Continuous Attributes
- scientific article; zbMATH DE number 4166895 (Why is no real title available?)
- Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
- On the quest for optimal rule learning heuristics
- ROC `n' rule learning -- towards a better understanding of covering algorithms
- Separate-and-conquer rule learning
- Statistical comparisons of classifiers over multiple data sets
Cited in
(9)- Learning rule sets and Sugeno integrals for monotonic classification problems
- FOLD-R++: a scalable toolset for automated inductive learning of default theories from mixed data
- On the approximability of the largest sphere rule ensemble classification problem
- A Comparison of Four Classification Systems Using Rule Sets Induced from Incomplete Data Sets by Local Probabilistic Approximations
- scientific article; zbMATH DE number 66821 (Why is no real title available?)
- FOLD-RM: A Scalable, Efficient, and Explainable Inductive Learning Algorithm for Multi-Category Classification of Mixed Data
- AI 2005: Advances in Artificial Intelligence
- Explainable and interpretable machine learning and data mining
- Interpretable optimisation-based approach for hyper-box classification
This page was built for publication: Efficient learning of large sets of locally optimal classification rules
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6097160)
