Research map / Graph learning / Knowledge and temporal graphs
Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
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 |
|---|---|---|---|
| use TDLG edge proximity features instead of the compared temporal embedding methods | edge classification · five real-world datasets | AUC | Helped |
| use TDLG edge proximity features instead of the compared methods | interpolative link outlier detection · five real-world datasets | AUC | Helped |
| use TDLG edge proximity features instead of the compared methods | extrapolative temporal link prediction · five real-world datasets | AUC | Helped |
| replace sparse TDLG row features with top 128 eigenvector features (ablation) | TDLG · edge classification, all reported datasets | AUC | Hurt |
| vary the time-decay scale across the tested range (ablation) | TDLG · BitcoinAlpha, BitcoinOTC, Escorts, WikiElect edge classification | AUC | Mixed |
| normalize TDLG adjacency with spectral or edge normalization rather than leaving it unnormalized (ablation) | TDLG · edge classification, tested datasets | AUC | Hurt |
Closest papers by meaning
- Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs (NeurIPS 2024 · similarity 0.88)
- TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction (NeurIPS 2025 · similarity 0.88)
- Improving Temporal Link Prediction via Temporal Walk Matrix Projection (NeurIPS 2024 · similarity 0.88)
- Continuous-Time Graph Representation with Sequential Survival Process (AAAI 2024 · similarity 0.87)
- Deep Representation Learning for Forecasting Recursive and Multi-Relational Events in Temporal Networks (AAAI 2025 · similarity 0.86)
- State Space Models on Temporal Graphs: A First-Principles Study (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.