Research map / Graph learning / Graph algorithms and clustering
On the Power of Gradual Network Alignment Using Dual-Perception Similarities
Jin-Duk Park, Cong Tran, Won-Yong Shin, Xin Cao
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 |
|---|---|---|---|
| use dual-perception similarity with gradual matching instead of the best prior method | Grad-Align · Douban | Acc: 75.54% | Improved |
| replace GCN/SAGE with GIN as the GNN backbone (ablation) | Grad-Align · Fb-Tw, Douban, Am-ID | Acc | Improved |
| use sum aggregator rather than mean or max (ablation) | Grad-Align-GIN · Fb-Tw, Douban, Am-ID | Acc | Improved |
| set GNN layers k=2 versus fewer or more (ablation) | Grad-Align · Fb-Tw, Douban, Am-ID | Acc | Improved |
| set Tversky alpha near n_t/n_s instead of Jaccard (alpha=beta=1) (ablation) | Grad-Align · Fb-Tw, Douban, Am-ID | Acc: n_t/n_s = 1, 0.29, and 0.95 | Improved |
| increase gradual matching iterations iter (ablation) | Grad-Align · Fb-Tw, Douban, Am-ID | Acc: iter=5 vs iter=1 | Improved |
| add prior seed nodes (t>0 versus t=0) (ablation) | Grad-Align · Fb-Tw | Acc | Improved |
| add prior seed nodes (t>0 versus t=0) (ablation) | Grad-Align · Douban, Am-ID | Acc | No clear effect |
| use Grad-Align instead of Grad-Align-1 ablation variant (ablation) | Grad-Align · Fb-Tw | Acc: 0.47 -> 0.96 | Improved |
| use Grad-Align instead of Grad-Align-1 ablation variant (ablation) | Grad-Align · Douban | Acc: 0.32 -> 0.59 | Improved |
| use Grad-Align instead of Grad-Align-1 ablation variant (ablation) | Grad-Align · Am-ID | Acc: 0.85 -> 0.96 | Improved |
Closest papers by meaning
- PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment (ICLR 2026 · similarity 0.90)
- Hierarchical Multi-Marginal Optimal Transport for Network Alignment (AAAI 2024 · similarity 0.89)
- Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval (NeurIPS 2024 · similarity 0.87)
- Chaining 2-FWL GNNs for Combinatorial Graph Alignment (NeurIPS 2026 · similarity 0.87)
- What Is Missing For Graph Homophily? Disentangling Graph Homophily For Graph Neural Networks (NeurIPS 2024 · similarity 0.85)
- Open-Set Cross-Network Node Classification via Unknown-Excluded Adversarial Graph Domain Alignment (AAAI 2025 · 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.
