Research map / Graph learning / GNN architectures
Graph Neural Ricci Flow: Evolving Feature from a Curvature Perspective
Jialong Chen, Bowen Deng, Zhen WANG, Chuan Chen, Zibin Zheng
Read the paperCheck your idea against 137,217 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.
Generalizes discrete Ricci flow to attributed graphs to evolve node features via edge curvature, showing curvature concentrates toward zero over time.
Problem
Understanding and designing graph neural networks from a differential-equation perspective, specifically how node features evolve on attributed graphs.
Approach
Extends discrete Ricci flow (DRF) to attributed graphs so node feature evolution is driven by edge curvature; shows DRF guarantees that each edge's curvature concentrates toward zero over time.
Key results
- DRF on attributed graphs guarantees that the curvature of each edge concentrates toward zero over time.
Experimental setup
Builds on: discrete Ricci flow
Closest papers by meaning
- Discrete Curvature Graph Information Bottleneck (AAAI 2025 · similarity 0.91)
- Effective Structural Encodings via Local Curvature Profiles (ICLR 2024 · similarity 0.89)
- Spectro-Riemannian Graph Neural Networks (ICLR 2025 · similarity 0.87)
- The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited (ICLR 2025 · similarity 0.87)
- Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning (AAAI 2024 · similarity 0.87)
- What do Graph Neural Networks learn? Insights from Tropical Geometry (NeurIPS 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.
