Research map / Graph learning / Graph self-supervised learning
GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes GraphMoRE, a mixture of Riemannian experts that routes graph nodes to different constant-curvature spaces to handle topological heterogeneity.
Problem
Real-world graphs have diverse topological patterns, and embedding them in a single constant-curvature space yields high-distortion, low-quality representations; this also limits graph foundation models.
Approach
Uses a mixture of experts where each expert embeds graph structure in a different Riemannian (constant-curvature) space, so heterogeneous regions can be matched to suitable geometries.
Limitations
- Full paper body not available; only the AAAI template text was provided, so details are unverified.
Closest papers by meaning
- Pseudo-Riemannian Graph Transformer (NeurIPS 2025 · similarity 0.90)
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.89)
- Curvature Regularization to Prevent Distortion in Graph Embedding (NeurIPS 2020 · similarity 0.89)
- Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning (AAAI 2024 · similarity 0.87)
- Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures (NeurIPS 2024 · similarity 0.87)
- Spectro-Riemannian Graph Neural Networks (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.