Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929422786887680 |
|---|---|
| author | Klarner, Leo Rudner, Tim G. J. Morris, Garrett M. Deane, Charlotte M. Teh, Yee Whye |
| author_facet | Klarner, Leo Rudner, Tim G. J. Morris, Garrett M. Deane, Charlotte M. Teh, Yee Whye |
| contents | Generative models have the potential to accelerate key steps in the discovery of novel molecular therapeutics and materials. Diffusion models have recently emerged as a powerful approach, excelling at unconditional sample generation and, with data-driven guidance, conditional generation within their training domain. Reliably sampling from high-value regions beyond the training data, however, remains an open challenge -- with current methods predominantly focusing on modifying the diffusion process itself. In this paper, we develop context-guided diffusion (CGD), a simple plug-and-play method that leverages unlabeled data and smoothness constraints to improve the out-of-distribution generalization of guided diffusion models. We demonstrate that this approach leads to substantial performance gains across various settings, including continuous, discrete, and graph-structured diffusion processes with applications across drug discovery, materials science, and protein design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11942 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design Klarner, Leo Rudner, Tim G. J. Morris, Garrett M. Deane, Charlotte M. Teh, Yee Whye Biomolecules Machine Learning Generative models have the potential to accelerate key steps in the discovery of novel molecular therapeutics and materials. Diffusion models have recently emerged as a powerful approach, excelling at unconditional sample generation and, with data-driven guidance, conditional generation within their training domain. Reliably sampling from high-value regions beyond the training data, however, remains an open challenge -- with current methods predominantly focusing on modifying the diffusion process itself. In this paper, we develop context-guided diffusion (CGD), a simple plug-and-play method that leverages unlabeled data and smoothness constraints to improve the out-of-distribution generalization of guided diffusion models. We demonstrate that this approach leads to substantial performance gains across various settings, including continuous, discrete, and graph-structured diffusion processes with applications across drug discovery, materials science, and protein design. |
| title | Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design |
| topic | Biomolecules Machine Learning |
| url | https://arxiv.org/abs/2407.11942 |