Research map / Graph learning / Graph self-supervised learning
PRUNE: Preserving Proximity and Global Ranking for Network Embedding
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add global node ranking objective (multi-task) to proximity-only TriFac (ablation) | PRUNE · Hep-Ph learning-to-rank | Spearman rank correlation: 0.554 -> 0.621 | Helped |
| add global node ranking objective (ablation) | PRUNE · Webspam learning-to-rank | AUC: 0.821 -> 0.853 | Helped |
| add global node ranking objective (ablation) | PRUNE · FB Wall Post learning-to-rank | AUC: 0.747 -> 0.765 | Helped |
| add global node ranking objective (ablation) | PRUNE · Hep-Ph regression | RMSE: 11.967 -> 11.720 | Helped |
| add global node ranking objective (ablation) | PRUNE · Webspam classification | AUC: 0.576 -> 0.637 | Helped |
| add global node ranking objective (ablation) | PRUNE · FB Wall Post classification | AUC: 0.763 -> 0.775 | Helped |
| add global node ranking objective (ablation) | PRUNE · Hep-Ph link prediction | AUC: 0.814 -> 0.861 | Helped |
| add global node ranking objective (ablation) | PRUNE · Webspam link prediction | AUC: 0.946 -> 0.973 | Helped |
| add global node ranking objective (ablation) | PRUNE · FB Wall Post link prediction | AUC: 0.858 -> 0.878 | Helped |
| Replace PRUNE with random-walk-based node2vec/DeepWalk embeddings | network embedding · Hep-Ph learning-to-rank | Spearman rank correlation: 0.621 -> 0.494 | Hurt |
| PRUNE vs baselines under increasing fraction of dropped edges | PRUNE · Hep-Ph and FB Wall Post learning-to-rank | RankCorr/AUC | Helped |
Closest papers by meaning
- Reconciling Competing Sampling Strategies of Network Embedding (NeurIPS 2023 · similarity 0.89)
- Community Preserving Network Embedding (AAAI 2017 · similarity 0.88)
- Non-Euclidean Mixture Model for Social Network Embedding (NeurIPS 2024 · similarity 0.87)
- A Topological Perspective on Demystifying GNN-Based Link Prediction Performance (ICLR 2024 · similarity 0.86)
- Link Prediction in Multilayer Networks via Cross-Network Embedding (AAAI 2024 · similarity 0.86)
- Community Detection Guarantees using Embeddings Learned by Node2Vec (NeurIPS 2024 · similarity 0.86)
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.