MoE-Guided Graph Diffusion for Oriented Molecule Design
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (28) · 23151-23159
DOI: 10.1609/aaai.v40i28.39482 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shuochen Li und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Designing molecules with desired properties, aka the oRiented molEcule Design (RED), is a fundamental task in chemistry and materials science. While graph diffusion models (GDMs) and reinforcement learning techniques (RL) show promise in molecule structure generation and property optimization stages individually, their integration in the unified RED task often suffers from poor compatibility. The large variance among candidate molecular structures generated by GDMs can be amplified in the iterative optimization process of RL, leading to slow and unstable convergence. In this work, motivated by the adaptive and divide-and-conquer characteristics of Mixture of Experts (MoE) architecture, we propose a novel framework called MoE-Guided Graph Diffusion Model (MEGD) that incorporates the MoE architecture to guide the orchestration of GDM and RL, promoting faster and more stable convergence in the design process. MEGD is evaluated on benchmark datasets optimizing the physical and chemical properties of AI-generated molecular structures. On all three datasets, our method outperforms the best of 9 alternative models by 7.73% on the target structural properties, while not penalizing other important application-level quality metrics of the generated molecules. A real-world case study on an emerging class of material, i.e., metal-organic framework, is also conducted, which further demonstrates the effectiveness of our method in accomplishing the RED task.
Zitieren
APA
Li, S., Guo, X., Tan, H., & Shi, L. (2026). MoE-Guided Graph Diffusion for Oriented Molecule Design. Proceedings of the AAAI Conference on Artificial Intelligence, 40(28), 23151-23159. https://doi.org/10.1609/aaai.v40i28.39482
Vancouver
Li S, Guo X, Tan H, Shi L. MoE-Guided Graph Diffusion for Oriented Molecule Design. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(28):23151-23159. doi:10.1609/aaai.v40i28.39482
BibTeX
@article{Li2026,
author = {Li, Shuochen and Guo, Xiangqi and Tan, Huobin and Shi, Lei},
title = {MoE-Guided Graph Diffusion for Oriented Molecule Design},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {28},
pages = {23151--23159},
doi = {10.1609/aaai.v40i28.39482}
}
EUVIMED