Research map / Graph learning / Knowledge and temporal graphs
Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic 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 |
|---|---|---|---|
| add temporal-biased sampling probability (ablation) | NeurTWs · CollegeMsg inductive | AUC: 0.918 -> 0.958 | Helped |
| add temporal-biased sampling probability (ablation) | NeurTWs · Taobao inductive | AUC: 0.932 -> 0.938 | No clear effect |
| add spatial-biased (degree) sampling probability (ablation) | NeurTWs · CollegeMsg inductive | AUC: 0.949 -> 0.958 | No clear effect |
| add spatial-biased (degree) sampling probability (ablation) | NeurTWs · Taobao inductive | AUC: 0.915 -> 0.938 | Helped |
| add exploitation-exploration trade-off probability (ablation) | NeurTWs · Taobao inductive | AUC: 0.926 -> 0.938 | Helped |
| add exploitation-exploration trade-off probability (ablation) | NeurTWs · CollegeMsg inductive | AUC: 0.957 -> 0.958 | No clear effect |
| add continuous evolution (ODE) in walk encoding (ablation) | NeurTWs · CollegeMsg inductive | AUC: 0.868 -> 0.958 | Helped |
| add continuous evolution (ODE) in walk encoding (ablation) | NeurTWs · Taobao inductive | AUC: 0.860 -> 0.938 | Helped |
| use contrastive loss instead of binary cross entropy (ablation) | NeurTWs · CollegeMsg inductive | AUC: 0.954 -> 0.958 | Helped |
| use contrastive loss instead of binary cross entropy (ablation) | NeurTWs · Taobao inductive | AUC: 0.935 -> 0.938 | No clear effect |
| binary instead of unitary anonymization | NeurTWs · Transductive link prediction | AUC: 0.9526 -> 0.9750 (CollegeMsg); 0.9100 -> 0.8911 (Taobao) | Mixed |
Closest papers by meaning
- Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models (ICML 2026 · similarity 0.90)
- DyRep: Learning Representations over Dynamic Graphs (ICLR 2019 · similarity 0.90)
- State Space Models on Temporal Graphs: A First-Principles Study (NeurIPS 2024 · similarity 0.90)
- A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generation (AAAI 2025 · similarity 0.89)
- Continuous-Time Graph Representation with Sequential Survival Process (AAAI 2024 · similarity 0.88)
- Improving Temporal Link Prediction via Temporal Walk Matrix Projection (NeurIPS 2024 · similarity 0.88)
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.