2024/07/16 by Leo Klarner, Tim G. J. Rudner, Klarner, Leo +7 · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Decision Sciences · #Biomolecules (q-bio.BM) #Computational Drug Discovery Methods #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimal Experimental Design Methods #Protein purification and stability
paper · pdf · doi:10.48550/arxiv.2407.11942
openalex publication_date 2024/07/16 · openalex created_date 2024/10/25 · openalex updated_date 2026/07/28
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.