Saved in:
Bibliographic Details
Main Authors: Cao, Haifang, Wang, Yu, Li, Timing, Yao, Xinjie, Zhu, Pengfei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22317
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910066368577536
author Cao, Haifang
Wang, Yu
Li, Timing
Yao, Xinjie
Zhu, Pengfei
author_facet Cao, Haifang
Wang, Yu
Li, Timing
Yao, Xinjie
Zhu, Pengfei
contents Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accurately within a single Riemannian manifold. While emerging mixed-curvature methods attempt to capture such diversity, they often rely on implicit, task-driven routing that lacks fundamental geometric grounding. To address this challenge, we propose a Geometric Mixture-of-Experts framework (GeoMoE) that adaptively fuses node representations across diverse Riemannian spaces to better accommodate multi-scale topological structures. At its core, GeoMoE leverages Ollivier-Ricci Curvature (ORC) as an intrinsic geometric prior to orchestrate the collaboration of specialized experts. Specifically, we design a graph-aware gating network that assigns node-specific fusion weights, regularized by a curvature-guided alignment loss to ensure interpretable and geometry-consistent routing. Additionally, we introduce a curvature-aware contrastive objective that promotes geometric discriminability by constructing positive and negative pairs according to curvature consistency. Extensive experiments on six benchmark datasets demonstrate that GeoMoE outperforms state-of-the-art baselines across diverse graph types.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22317
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
Cao, Haifang
Wang, Yu
Li, Timing
Yao, Xinjie
Zhu, Pengfei
Machine Learning
Artificial Intelligence
Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accurately within a single Riemannian manifold. While emerging mixed-curvature methods attempt to capture such diversity, they often rely on implicit, task-driven routing that lacks fundamental geometric grounding. To address this challenge, we propose a Geometric Mixture-of-Experts framework (GeoMoE) that adaptively fuses node representations across diverse Riemannian spaces to better accommodate multi-scale topological structures. At its core, GeoMoE leverages Ollivier-Ricci Curvature (ORC) as an intrinsic geometric prior to orchestrate the collaboration of specialized experts. Specifically, we design a graph-aware gating network that assigns node-specific fusion weights, regularized by a curvature-guided alignment loss to ensure interpretable and geometry-consistent routing. Additionally, we introduce a curvature-aware contrastive objective that promotes geometric discriminability by constructing positive and negative pairs according to curvature consistency. Extensive experiments on six benchmark datasets demonstrate that GeoMoE outperforms state-of-the-art baselines across diverse graph types.
title Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.22317