Neurally-Guided Structure Inference

by   Sidi Lu, et al.

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.


Hybrid Data-Driven Closure Strategies for Reduced Order Modeling

In this paper, we propose hybrid data-driven ROM closures for fluid flow...

An accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data

We present a hybrid model/model-free data-driven approach to solve poroe...

Hybridizing Physical and Data-driven Prediction Methods for Physicochemical Properties

We present a generic way to hybridize physical and data-driven methods f...

Data-Driven Abductive Inference of Library Specifications

Programmers often leverage data structure libraries that provide useful ...

Neural Approaches for Data Driven Dependency Parsing in Sanskrit

Data-driven approaches for dependency parsing have been of great interes...

Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion

In the fields of image restoration and image fusion, model-driven method...

Scalable Structure Learning for Probabilistic Soft Logic

Statistical relational frameworks such as Markov logic networks and prob...