Research map / Graph learning / GNN architectures
OPEN: Orthogonal Propagation with Ego-Network Modeling
Liang Yang, Lina Kang, Qiuliang Zhang, Mengzhe Li, Bingxin Niu, Dongxiao He, Zhen Wang, Chuan Wang, Xiaochun Cao, Yuanfang Guo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace GAT irrelevant propagation with ego-network relevant propagation (K=1) (ablation) | GAT · Cora, Citeseer, Pubmed | accuracy | Improved |
| add orthogonal multi-channel propagation (K>1) (ablation) | OPEN with K=1 · Cora, Citeseer, Pubmed | accuracy | Improved |
| increase number of channels K (ablation) | OPEN vs GAT · Cora, Citeseer, Pubmed | accuracy | Mixed |
| use OPEN instead of GAT as depth grows | GAT · Cora, Citeseer, Pubmed | accuracy | Improved |
| use OPEN instead of GAT under random added noisy edges | GAT · Cora, Citeseer, Pubmed | accuracy | Improved |
| use OPEN instead of GAT | GAT · Cora | micro-F1: 87.37 -> 89.31 | Improved |
| use OPEN instead of GCNII | GCNII · Citeseer | micro-F1: 77.08 -> 80.42 | Improved |
| use OPEN instead of GPRGNN | GPRGNN · Computer | micro-F1: 89.43 -> 90.93 | Improved |
| use OPEN instead of DMP | DMP · CS | micro-F1: 95.02 -> 94.99 | No clear effect |
Closest papers by meaning
- Simple Orthogonal Graph Representation Learning (Student Abstract) (AAAI 2024 · similarity 0.87)
- A Topological Perspective on Demystifying GNN-Based Link Prediction Performance (ICLR 2024 · similarity 0.86)
- AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks (AAAI 2025 · similarity 0.85)
- A Signed Graph Approach to Understanding and Mitigating Oversmoothing (NeurIPS 2025 · similarity 0.85)
- Integrating Co-Training with Edge Discrimination to Enhance Graph Neural Networks Under Heterophily (AAAI 2025 · similarity 0.85)
- Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables (NeurIPS 2026 · similarity 0.85)
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.
