# Neurally-Guided Structure Inference

arXiv: https://arxiv.org/abs/1906.07304 · HTML: https://mlsanity.com/paper/1906.07304/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2019.

## Built on by (most cited first, 2 of 2)

- [ShapeMOD: Macro Operation Discovery for 3D Shape Programs](https://mlsanity.com/paper/2104.06392/) (2021)
- [Neurosymbolic Decision Trees](https://mlsanity.com/paper/2503.08762/) (2025)

## Abstract (arXiv)

Most structure inference methods either rely on exhaustive search or are purely data-driven. Exhaustive search robustly infers the structure of arbitrarily complex data, but it is slow. Data-driven methods allow efficient inference, but do not generalize when test data have more complex structures than training data. In this paper, we propose a hybrid inference algorithm, the Neurally-Guided Structure Inference (NG-SI), keeping the advantages of both search-based and data-driven methods. The key idea of NG-SI is to use a neural network to guide the hierarchical, layer-wise search over the compositional space of structures. We evaluate our algorithm on two representative structure inference tasks: probabilistic matrix decomposition and symbolic program parsing. It outperforms data-driven and search-based alternatives on both tasks.