Research map / Graph learning / Graph self-supervised learning
Pseudo-Riemannian Graph Transformer
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a graph transformer operating in pseudo-Riemannian manifolds to embed graphs with diverse, non-uniform curvature structures.
Problem
Real-world graphs have complex topology not captured by uniform-curvature manifolds (hyperbolic or spherical); existing pseudo-Riemannian graph embedding approaches have limitations (the abstract is truncated).
Approach
Extends graph transformers into pseudo-Riemannian manifolds, which generalize hyperbolic and spherical geometry, to model graphs with mixed curvature structure.
Closest papers by meaning
- Pseudo-Riemannian Graph Convolutional Networks (NeurIPS 2022 · similarity 0.93)
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.91)
- Spectro-Riemannian Graph Neural Networks (ICLR 2025 · similarity 0.87)
- Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning (AAAI 2024 · similarity 0.87)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.86)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.86)
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.