Deterministic Decoding for Discrete Data in Variational Autoencoders
This addresses a bottleneck in generative modeling for discrete data, offering a method to enhance latent code utilization, though it appears incremental as it builds on existing VAE frameworks.
The paper tackles the problem of variational autoencoders ignoring latent codes when modeling discrete data by introducing a deterministic decoder that selects highest-scoring tokens, which improves manifold structure and is demonstrated on molecular generation and optimization datasets.
Variational autoencoders are prominent generative models for modeling discrete data. However, with flexible decoders, they tend to ignore the latent codes. In this paper, we study a VAE model with a deterministic decoder (DD-VAE) for sequential data that selects the highest-scoring tokens instead of sampling. Deterministic decoding solely relies on latent codes as the only way to produce diverse objects, which improves the structure of the learned manifold. To implement DD-VAE, we propose a new class of bounded support proposal distributions and derive Kullback-Leibler divergence for Gaussian and uniform priors. We also study a continuous relaxation of deterministic decoding objective function and analyze the relation of reconstruction accuracy and relaxation parameters. We demonstrate the performance of DD-VAE on multiple datasets, including molecular generation and optimization problems.