Graph Geometry Interaction Learning

2020/10/23 by Shichao Zhu, Zhu, Shichao, Shirui Pan +9 · 3 citations
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Complex Network Analysis Techniques #FOS: Computer and information sciences #Graph Theory and Algorithms #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2010.12135

openalex publication_date 2020/10/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

While numerous approaches have been developed to embed graphs into either Euclidean or hyperbolic spaces, they do not fully utilize the information available in graphs, or lack the flexibility to model intrinsic complex graph geometry. To utilize the strength of both Euclidean and hyperbolic geometries, we develop a novel Geometry Interaction Learning (GIL) method for graphs, a well-suited and efficient alternative for learning abundant geometric properties in graph. GIL captures a more informative internal structural features with low dimensions while maintaining conformal invariance of each space. Furthermore, our method endows each node the freedom to determine the importance of each geometry space via a flexible dual feature interaction learning and probability assembling mechanism. Promising experimental results are presented for five benchmark datasets on node classification and link prediction tasks.

Citations

• Geometric Deep Learning: Going beyond Euclidean data
• Neural Message Passing for Quantum Chemistry
• Fast Graph Representation Learning with PyTorch Geometric
• Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
• Hyperbolic Graph Convolutional Neural Networks
• A Comprehensive Survey on Graph Neural Networks

Cited by

• Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detection
• PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning
• Hyperbolic Deep Learning for Foundation Models: A Survey

Related

• Node-Specific Space Selection via Localized Geometric Hyperbolicity in Graph Neural Networks
• Geometry Interaction Knowledge Graph Embeddings
• GraphShaper: Geometry-aware Alignment for Improving Transfer Learning in Text-Attributed Graphs
• Hyperbolic Graph Representation Learning: A Tutorial
• Hyperbolic Graph Neural Networks: A Review of Methods and Applications