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.


The Neurally-Guided Structure Inference for Matrix Decomposition [TensorFlow (Official)].

=Related Publications

Exploiting compositionality to explore a large space of model structures

Roger B. Grosse, Ruslan Salakhutdinov, William T. Freeman, and Joshua B. Tenenbaum