atlas

Research map / Graph learning / Graph self-supervised learning

Link Prediction with Persistent Homology: An Interactive View

ICML 2021 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 6 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use pairwise rather than nodewise topological features (ablation)TLC-GNN · PubMedROC-AUC: 96.91±0.002 -> 97.03±0.001Helped
Use pairwise rather than nodewise topological features (ablation)TLC-GNN · PhotoROC-AUC: 97.91±0.001 -> 98.23±0.001Helped
Use pairwise rather than nodewise topological features (ablation)TLC-GNN · ComputersROC-AUC: 97.03±0.001 -> 97.90±0.001Helped
Use Ollivier-Ricci curvature rather than DRNL as the distance filter (ablation)TLC-GNN · PubMed, Photo, ComputersROC-AUC: 96.89±0.002 -> 97.03±0.001; 97.61±0.003 -> 98.23±0.001; 97.23±0.003 -> 97.90±0.001Mixed
Add pairwise topological features to the link predictorTLC-GNN · PPI samples 1–5ROC-AUCMixed
Replace matrix reduction with the graph-based faster persistence algorithmExtended persistence computation · PubMed, Photo, Computersrunning time per edge: 0.0068 -> 0.0027; 1.6557 -> 1.1176; 4.6531 -> 2.7033Helped

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