Topology-Aware Multiscale Mixture of Experts for Efficient Molecular Property Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Long D., Xia, Kelin, Nguyen, Binh P.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912831917522944
author Nguyen, Long D.
Xia, Kelin
Nguyen, Binh P.
author_facet Nguyen, Long D.
Xia, Kelin
Nguyen, Binh P.
contents Many molecular properties depend on 3D geometry, where non-covalent interactions, stereochemical effects, and medium- to long-range forces are determined by spatial distances and angles that cannot be uniquely captured by a 2D bond graph. Yet most 3D molecular graph neural networks still rely on globally fixed neighborhood heuristics, typically defined by distance cutoffs and maximum neighbor limits, to define local message-passing neighborhoods, leading to rigid, data-agnostic interaction budgets. We propose Multiscale Interaction Mixture of Experts (MI-MoE) to adapt interaction modeling across geometric regimes. Our contributions are threefold: (1) we introduce a distance-cutoff expert ensemble that explicitly captures short-, mid-, and long-range interactions without committing to a single cutoff; (2) we design a topological gating encoder that routes inputs to experts using filtration-based descriptors, including persistent homology features, summarizing how connectivity evolves across radii; and (3) we show that MI-MoE is a plug-in module that consistently improves multiple strong 3D molecular backbones across diverse molecular and polymer property prediction benchmark datasets, covering both regression and classification tasks. These results highlight topology-aware multiscale routing as an effective principle for 3D molecular graph learning.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12637
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Topology-Aware Multiscale Mixture of Experts for Efficient Molecular Property Prediction
Nguyen, Long D.
Xia, Kelin
Nguyen, Binh P.
Machine Learning
Artificial Intelligence
Quantitative Methods
Many molecular properties depend on 3D geometry, where non-covalent interactions, stereochemical effects, and medium- to long-range forces are determined by spatial distances and angles that cannot be uniquely captured by a 2D bond graph. Yet most 3D molecular graph neural networks still rely on globally fixed neighborhood heuristics, typically defined by distance cutoffs and maximum neighbor limits, to define local message-passing neighborhoods, leading to rigid, data-agnostic interaction budgets. We propose Multiscale Interaction Mixture of Experts (MI-MoE) to adapt interaction modeling across geometric regimes. Our contributions are threefold: (1) we introduce a distance-cutoff expert ensemble that explicitly captures short-, mid-, and long-range interactions without committing to a single cutoff; (2) we design a topological gating encoder that routes inputs to experts using filtration-based descriptors, including persistent homology features, summarizing how connectivity evolves across radii; and (3) we show that MI-MoE is a plug-in module that consistently improves multiple strong 3D molecular backbones across diverse molecular and polymer property prediction benchmark datasets, covering both regression and classification tasks. These results highlight topology-aware multiscale routing as an effective principle for 3D molecular graph learning.
title Topology-Aware Multiscale Mixture of Experts for Efficient Molecular Property Prediction
topic Machine Learning
Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2601.12637