Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Tree-Structured Variational Autoencoder
Richard Shin, Alexander A. Alemi, Geoffrey Irving, Oriol Vinyals
Nov 04, 2016 (modified: Nov 04, 2016)ICLR 2017 conference submissionreaders: everyone
Abstract:Many kinds of variable-sized data we would like to model contain an internal hierarchical structure in the form of a tree, including source code, formal logical statements, and natural language sentences with parse trees. For such data it is natural to consider a model with matching computational structure. In this work, we introduce a variational autoencoder-based generative model for tree-structured data. We evaluate our model on a synthetic dataset, and a dataset with applications to automated theorem proving. By learning a latent representation over trees, our model can achieve similar test log likelihood to a standard autoregressive decoder, but with the number of sequentially dependent computations proportional to the depth of the tree instead of the number of nodes in the tree.
Enter your feedback below and we'll get back to you as soon as possible.