Research map / Graph learning / Graph self-supervised learning
Subgraph Encoding with Bicentric Sphere Node Labeling and Pooling for Link Prediction
Zhihong Fang, Shaolin Tan, Qiu Fang, Zhe LI, Qing Gao
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 |
|---|---|---|---|
| extend subgraph from 1 hop to 2 hops (ablation) | BS-SubGNN · C.ele / SMG / EML / HPD | AUC: e.g. EML 91.36 -> 92.79 | Improved |
| extend subgraph from 1 hop to 2 hops (ablation) | BS-SubGNN · ADV | AUC: 96.27 -> 95.67 | Hurt |
| use one-hop BS-SubGNN against SEAL (h=2) on EML | BS-SubGNN · EML | AUC: 91.36 vs 92.01 | Hurt |
| use BS-SubGNN (h=2) instead of LGLP (h=2) | BS-SubGNN · C.ele | AUC: 90.16 -> 91.43 | Improved |
| use BS-SubGNN (h=2) instead of NNESF (h=2) | BS-SubGNN · ZWL | AUC: 97.98 -> 98.49 | Improved |
| use BS-SubGNN (h=2) instead of LGLP (h=2) | BS-SubGNN · GRQ | AUC: 97.68 vs 97.68 | No clear effect |
| use BFS-based bicentric labeling (bound h+1) instead of SEAL DRNL labeling | BS-SubGNN · C.ele | time (s): 100.83 s -> 8.69 s | Improved |
| use BS-SubGNN labeling instead of NNESF | BS-SubGNN · YST | time (s): 50.27 s -> 25.07 s | Improved |
Closest papers by meaning
- GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction (NeurIPS 2026 · similarity 0.89)
- A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (NeurIPS 2024 · similarity 0.88)
- Union Subgraph Neural Networks (AAAI 2024 · similarity 0.88)
- Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning (ICML 2024 · similarity 0.87)
- Structural Information Enhanced Graph Representation for Link Prediction (AAAI 2024 · similarity 0.87)
- A Topological Perspective on Demystifying GNN-Based Link Prediction Performance (ICLR 2024 · similarity 0.87)
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.
