Grammar Variational Autoencoder
This addresses a key bottleneck in generating valid discrete structures for applications like symbolic regression and molecular synthesis, representing a novel method rather than an incremental improvement.
The paper tackled the problem of generative modeling for discrete data like arithmetic expressions and molecular structures, where existing methods often produce invalid outputs, by proposing a variational autoencoder that encodes and decodes directly from parse trees to ensure validity, resulting in more coherent latent spaces and improved performance in Bayesian optimization for symbolic regression and molecular synthesis.
Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular structures still poses significant challenges. Crucially, state-of-the-art methods often produce outputs that are not valid. We make the key observation that frequently, discrete data can be represented as a parse tree from a context-free grammar. We propose a variational autoencoder which encodes and decodes directly to and from these parse trees, ensuring the generated outputs are always valid. Surprisingly, we show that not only does our model more often generate valid outputs, it also learns a more coherent latent space in which nearby points decode to similar discrete outputs. We demonstrate the effectiveness of our learned models by showing their improved performance in Bayesian optimization for symbolic regression and molecular synthesis.