MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

2026-02-19

AI Summary

Existing molecular graph diffusion models often struggle with low chemical validity and difficulty in satisfying target properties. This work proposes MolHIT, a novel framework that introduces, for the first time, a hierarchical discrete diffusion mechanism into graph-based diffusion models. By integrating chemically informed multi-class encodings and atom representations decoupled according to chemical roles, MolHIT significantly enhances generation quality. The method achieves nearly 100% chemical validity on the MOSES dataset, establishing a new state-of-the-art for graph diffusion models and substantially outperforming 1D baselines. Furthermore, it demonstrates exceptional performance in multi-property-guided generation and scaffold extension tasks, highlighting its versatility and effectiveness in structure-based molecular design.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

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.

Problem

• molecular graph generation
• diffusion models
• chemical validity
• property optimization
• discrete diffusion

Innovation

• Hierarchical Discrete Diffusion
• Molecular Graph Generation
• Chemical Validity
• Decoupled Atom Encoding
• Diffusion Models