# Towards Efficient Active Learning of PDFA

arXiv: https://arxiv.org/abs/2206.09004 · HTML: https://mlsanity.com/paper/2206.09004/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 15 references that are in the map.
- First posted on arXiv 17 Jun 2022.

## Builds on (most cited first, 2 of 2)

- [Learning Deterministic Weighted Automata with Queries and Counterexamples](https://mlsanity.com/paper/1910.13895/) (2019)
- [L*-Based Learning of Markov Decision Processes (Extended Version)](https://mlsanity.com/paper/1906.12239/) (2019)

## Built on by (most cited first, 3 of 3)

- [Differentially Private 2D Human Pose Estimation](https://mlsanity.com/paper/2504.10190/) (2025)
- [Congruence-based Learning of Probabilistic Deterministic Finite Automata](https://mlsanity.com/paper/2412.09760/) (2024)
- [Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication](https://mlsanity.com/paper/2603.21305/) (2026)

## Abstract (arXiv)

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.