Actively Learning what makes a Discrete Sequence Valid
This addresses a key bottleneck in discrete generative models for researchers and practitioners, but it is incremental as it builds on existing active learning techniques.
The paper tackles the problem of generative deep learning models producing invalid discrete sequences by proposing a deep recurrent validator model that learns the probability of a partial sequence being the start of a valid full sequence, and demonstrates its ability to distinguish valid from invalid sequences on a synthetic dataset.
Deep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensional discrete spaces. These methods work by representing discrete objects as sequences, for which powerful sequence-based deep models can be employed. Unfortunately, these techniques are significantly hindered by the fact that these generative models often produce invalid sequences. As a step towards solving this problem, we propose to learn a deep recurrent validator model. Given a partial sequence, our model learns the probability of that sequence occurring as the beginning of a full valid sequence. Thus this identifies valid versus invalid sequences and crucially it also provides insight about how individual sequence elements influence the validity of discrete objects. To learn this model we propose an approach inspired by seminal work in Bayesian active learning. On a synthetic dataset, we demonstrate the ability of our model to distinguish valid and invalid sequences. We believe this is a key step toward learning generative models that faithfully produce valid discrete objects.