用分层离散扩散模型生成分子图，化学有效性首次接近完美。
MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
- 分层离散扩散建模，融合化学先验知识
- 在MOSES数据集上实现近乎完美的化学有效性
- 适合药物发现与材料设计中的多属性分子生成
基于扩散模型的分子生成已成为人工智能驱动药物发现和材料科学的有前景方向。尽管图结构扩散模型因二维分子图的离散特性被广泛采用，但现有方法仍存在化学有效性低、性能难以达到一维建模水平的问题。本文提出MolHIT，一种突破性分子图生成框架，基于分层离散扩散模型，将化学先验编码至额外类别，并采用解耦原子编码机制，按化学角色分离原子类型。MolHIT在MOSES数据集上首次实现接近完美的化学有效性，超越多个强基准的一维模型，在多指标上达到新最佳性能。此外，在下游任务中表现出色，包括多属性引导生成与骨架扩展。
原文摘要 · Abstract (English)
Molecular generation with diffusion models has emerged as a promising direction for AI-driven drug discovery and materials science. While graph diffusion models have been widely adopted due to the discrete nature of 2D molecular graphs, existing models suffer from low chemical validity and struggle to meet the desired properties compared to 1D modeling. In this work, we introduce MolHIT, a powerful molecular graph generation framework that overcomes long-standing performance limitations in existing methods. MolHIT is based on the Hierarchical Discrete Diffusion Model, which generalizes discrete diffusion to additional categories that encode chemical priors, and decoupled atom encoding that splits the atom types according to their chemical roles. Overall, MolHIT achieves new state-of-the-art performance on the MOSES dataset with near-perfect validity for the first time in graph diffusion, surpassing strong 1D baselines across multiple metrics. We further demonstrate strong performance in downstream tasks, including multi-property guided generation and scaffold extension.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。