Towards Efficient Active Learning of PDFA

TL;DR

This paper introduces a novel active learning algorithm for Probabilistic Deterministic Finite Automata (PDFA) that improves efficiency by leveraging a new state congruence, quantization, and a tree-based data structure, leading to better performance.

Contribution

The paper presents a new active learning method for PDFA that incorporates a state congruence considering next-symbol distributions, quantization for distribution differences, and an efficient data structure.

Findings

Significant performance improvements over existing methods

Effective handling of distribution differences through quantization

Efficient data structure enables faster learning

Abstract

We propose a new active learning algorithm for PDFA based on three main aspects: a congruence over states which takes into account next-symbol probability distributions, a quantization that copes with differences in distributions, and an efficient tree-based data structure. Experiments showed significant performance gains with respect to reference implementations.