Human in the Loop: Interactive Passive Automata Learning via Evidence-Driven State-Merging Algorithms

TL;DR

This paper introduces an interactive evidence-driven state-merging algorithm that incorporates human expertise to improve the learning of finite state automata from imperfect data sources.

Contribution

It presents a novel interactive approach to automata learning that leverages human input to guide the evidence-driven state-merging process.

Findings

Enhanced automata learning accuracy with human interaction

Better handling of noisy and incomplete data sources

Facilitated incorporation of domain knowledge

Abstract

We present an interactive version of an evidence-driven state-merging (EDSM) algorithm for learning variants of finite state automata. Learning these automata often amounts to recovering or reverse engineering the model generating the data despite noisy, incomplete, or imperfectly sampled data sources rather than optimizing a purely numeric target function. Domain expertise and human knowledge about the target domain can guide this process, and typically is captured in parameter settings. Often, domain expertise is subconscious and not expressed explicitly. Directly interacting with the learning algorithm makes it easier to utilize this knowledge effectively.