Research map / Graph learning / Knowledge and temporal graphs
Towards Fine-Grained Temporal Network Representation via Time-Reinforced Random Walk
Zhining Liu, Dawei Zhou, Yada Zhu, Jinjie Gu, Jingrui He
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| add bi-level context sampling (vs uniform start-node distribution) (ablation) | FiGTNE-TRRW · DBLP/Taobao/Epinion/Criteo node classification | Micro-F1: +0.5% to +3.9% relative | Improved |
| add bi-level context sampling (vs uniform start-node distribution) (ablation) | FiGTNE-TRRW · four datasets link prediction | AUC: +0.9% to +4.0% relative | Improved |
| time-reinforced random walk with temporal context vs static/snapshot baselines | FiGTNE-TRRW · DBLP, Taobao, Epinion, Criteo | Micro-F1 | Improved |
| temporal context in link prediction | FiGTNE-TRRW · link prediction | AUC | Mixed |
| snapshot aggregation (TNE) vs static embedding | TNE · node classification and link prediction | Micro-F1/AUC | Hurt |
| faster weight evolution (larger delta, smaller update interval K) | TRRW · Taobao | Micro-F1 | Improved |
Closest papers by meaning
- Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs (ICLR 2023 · similarity 0.90)
- Continuous-Time Graph Representation with Sequential Survival Process (AAAI 2024 · similarity 0.87)
- Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs (NeurIPS 2024 · similarity 0.87)
- Improving Temporal Link Prediction via Temporal Walk Matrix Projection (NeurIPS 2024 · similarity 0.86)
- Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis (AAAI 2024 · similarity 0.86)
- TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction (NeurIPS 2025 · 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.
