# Recursive Tree Grammar Autoencoders

arXiv: https://arxiv.org/abs/2012.02097 · HTML: https://mlsanity.com/paper/2012.02097/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Grammar-based Ordinary Differential Equation Discovery](https://mlsanity.com/paper/2504.02630/) (2025)
- [Project proposal: A modular reinforcement learning based automated theorem prover](https://mlsanity.com/paper/2209.02562/) (2022)
- [gym-saturation: Gymnasium environments for saturation provers (System description)](https://mlsanity.com/paper/2309.09022/) (2023)
- [Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generation](https://mlsanity.com/paper/2411.05472/) (2024)
- [ast2vec: Utilizing Recursive Neural Encodings of Python Programs](https://mlsanity.com/paper/2103.11614/) (2021)

## Abstract (arXiv)

Machine learning on trees has been mostly focused on trees as input to algorithms. Much less research has investigated trees as output, which has many applications, such as molecule optimization for drug discovery, or hint generation for intelligent tutoring systems. In this work, we propose a novel autoencoder approach, called recursive tree grammar autoencoder (RTG-AE), which encodes trees via a bottom-up parser and decodes trees via a tree grammar, both learned via recursive neural networks that minimize the variational autoencoder loss. The resulting encoder and decoder can then be utilized in subsequent tasks, such as optimization and time series prediction. RTG-AEs are the first model to combine variational autoencoders, grammatical knowledge, and recursive processing. Our key message is that this unique combination of all three elements outperforms models which combine any two of the three. In particular, we perform an ablation study to show that our proposed method improves the autoencoding error, training time, and optimization score on synthetic as well as real datasets compared to four baselines. We further prove that RTG-AEs parse and generate trees in linear time and are expressive enough to handle all regular tree grammars.