Neurally-Guided Structure Inference
Abstract
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.
Keywords
Cite
@article{arxiv.1906.07304,
title = {Neurally-Guided Structure Inference},
author = {Sidi Lu and Jiayuan Mao and Joshua B. Tenenbaum and Jiajun Wu},
journal= {arXiv preprint arXiv:1906.07304},
year = {2019}
}
Comments
Proceedings of the 36th International Conference on Machine Learning (ICML 2019). First two authors contributed equally. Project page: http://ngsi.csail.mit.edu