Neurally-guided structure inference
Author(s)
Lu, Sidi; Mao, Jiayuan; Tenenbaum, Joshua B; Wu, Jiajun
DownloadPublished version (1012.Kb)
Publisher Policy
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
© 36th International Conference on Machine Learning, ICML 2019. All rights reserved. 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.
Date issued
2019-01Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences; Center for Brains, Minds, and MachinesJournal
36th International Conference on Machine Learning, ICML 2019
Citation
Lu, S, Mao, J, Tenenbaum, JB and Wu, J. 2019. "Neurally-guided structure inference." 36th International Conference on Machine Learning, ICML 2019, 2019-June.
Version: Final published version