Improving Discrete Diffusion Models via Structured Preferential Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Rissanen, Severi, Heinonen, Markus, Solin, Arno
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914814676172800
author Rissanen, Severi
Heinonen, Markus
Solin, Arno
author_facet Rissanen, Severi
Heinonen, Markus
Solin, Arno
contents In the domains of image and audio, diffusion models have shown impressive performance. However, their application to discrete data types, such as language, has often been suboptimal compared to autoregressive generative models. This paper tackles the challenge of improving discrete diffusion models by introducing a structured forward process that leverages the inherent information hierarchy in discrete categories, such as words in text. Our approach biases the generative process to produce certain categories before others, resulting in a notable improvement in log-likelihood scores on the text8 dataset. This work paves the way for more advances in discrete diffusion models with potentially significant enhancements in performance.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17889
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Discrete Diffusion Models via Structured Preferential Generation
Rissanen, Severi
Heinonen, Markus
Solin, Arno
Machine Learning
In the domains of image and audio, diffusion models have shown impressive performance. However, their application to discrete data types, such as language, has often been suboptimal compared to autoregressive generative models. This paper tackles the challenge of improving discrete diffusion models by introducing a structured forward process that leverages the inherent information hierarchy in discrete categories, such as words in text. Our approach biases the generative process to produce certain categories before others, resulting in a notable improvement in log-likelihood scores on the text8 dataset. This work paves the way for more advances in discrete diffusion models with potentially significant enhancements in performance.
title Improving Discrete Diffusion Models via Structured Preferential Generation
topic Machine Learning
url https://arxiv.org/abs/2405.17889