AI Paper Atlas

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

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 0 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
extend subgraph from 1 hop to 2 hops (ablation)BS-SubGNN · C.ele / SMG / EML / HPDAUC: e.g. EML 91.36 -> 92.79Improved
extend subgraph from 1 hop to 2 hops (ablation)BS-SubGNN · ADVAUC: 96.27 -> 95.67Hurt
use one-hop BS-SubGNN against SEAL (h=2) on EMLBS-SubGNN · EMLAUC: 91.36 vs 92.01Hurt
use BS-SubGNN (h=2) instead of LGLP (h=2)BS-SubGNN · C.eleAUC: 90.16 -> 91.43Improved
use BS-SubGNN (h=2) instead of NNESF (h=2)BS-SubGNN · ZWLAUC: 97.98 -> 98.49Improved
use BS-SubGNN (h=2) instead of LGLP (h=2)BS-SubGNN · GRQAUC: 97.68 vs 97.68No clear effect
use BFS-based bicentric labeling (bound h+1) instead of SEAL DRNL labelingBS-SubGNN · C.eletime (s): 100.83 s -> 8.69 sImproved
use BS-SubGNN labeling instead of NNESFBS-SubGNN · YSTtime (s): 50.27 s -> 25.07 sImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy