DeepAI AI Chat
Log In Sign Up

Categorical Normalizing Flows via Continuous Transformations

by   Phillip Lippe, et al.
University of Amsterdam
Google Inc

Despite their popularity, to date, the application of normalizing flows on categorical data stays limited. The current practice of using dequantization to map discrete data to a continuous space is inapplicable as categorical data has no intrinsic order. Instead, categorical data have complex and latent relations that must be inferred, like the synonymy between words. In this paper, we investigate Categorical Normalizing Flows, that is normalizing flows for categorical data. By casting the encoding of categorical data in continuous space as a variational inference problem, we jointly optimize the continuous representation and the model likelihood. To maintain unique decoding, we learn a partitioning of the latent space by factorizing the posterior. Meanwhile, the complex relations between the categorical variables are learned by the ensuing normalizing flow, thus maintaining a close-to exact likelihood estimate and making it possible to scale up to a large number of categories. Based on Categorical Normalizing Flows, we propose GraphCNF a permutation-invariant generative model on graphs, outperforming both one-shot and autoregressive flow-based state-of-the-art on molecule generation.


page 1

page 2

page 3

page 4


Argmax Flows and Multinomial Diffusion: Towards Non-Autoregressive Language Models

The field of language modelling has been largely dominated by autoregres...

Discrete Denoising Flows

Discrete flow-based models are a recently proposed class of generative m...

Representational Rényi heterogeneity

A discrete system's heterogeneity is measured by the Rényi heterogeneity...

Categorical Representation Learning and RG flow operators for algorithmic classifiers

Following the earlier formalism of the categorical representation learni...

AdaCat: Adaptive Categorical Discretization for Autoregressive Models

Autoregressive generative models can estimate complex continuous data di...

Semi-Discrete Normalizing Flows through Differentiable Tessellation

Mapping between discrete and continuous distributions is a difficult tas...

Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow

Flow models have recently made great progress at modeling quantized sens...