Cliqueformer: Model-Based Optimization with Structured Transformers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kuba, Jakub Grudzien, Abbeel, Pieter, Levine, Sergey
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911526887096320
author Kuba, Jakub Grudzien
Abbeel, Pieter
Levine, Sergey
author_facet Kuba, Jakub Grudzien
Abbeel, Pieter
Levine, Sergey
contents Large neural networks excel at prediction tasks, but their application to design problems, such as protein engineering or materials discovery, requires solving offline model-based optimization (MBO) problems. While predictive models may not directly translate to effective design, recent MBO algorithms incorporate reinforcement learning and generative modeling approaches. Meanwhile, theoretical work suggests that exploiting the target function's structure can enhance MBO performance. We present Cliqueformer, a transformer-based architecture that learns the black-box function's structure through functional graphical models (FGM), addressing distribution shift without relying on explicit conservative approaches. Across various domains, including chemical and genetic design tasks, Cliqueformer demonstrates superior performance compared to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13106
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cliqueformer: Model-Based Optimization with Structured Transformers
Kuba, Jakub Grudzien
Abbeel, Pieter
Levine, Sergey
Machine Learning
Artificial Intelligence
Large neural networks excel at prediction tasks, but their application to design problems, such as protein engineering or materials discovery, requires solving offline model-based optimization (MBO) problems. While predictive models may not directly translate to effective design, recent MBO algorithms incorporate reinforcement learning and generative modeling approaches. Meanwhile, theoretical work suggests that exploiting the target function's structure can enhance MBO performance. We present Cliqueformer, a transformer-based architecture that learns the black-box function's structure through functional graphical models (FGM), addressing distribution shift without relying on explicit conservative approaches. Across various domains, including chemical and genetic design tasks, Cliqueformer demonstrates superior performance compared to existing methods.
title Cliqueformer: Model-Based Optimization with Structured Transformers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.13106