Research map / Probabilistic and scientific modeling / Dynamical systems
Neural Latent Space Model for Dynamic Networks and Temporal Knowledge 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 NLSM instead of the strongest listed baseline | Single-step link forecasting · Enron | Micro-AUC: 85.71 ± 0.3 -> 87.05 ± 0.3 | Helped |
| Use NLSM instead of the strongest listed baseline | Single-step link forecasting · UCI | Micro-AUC: 81.03 ± 0.2 -> 86.24 ± 0.4 | Helped |
| Use NLSM instead of the strongest listed baseline | Single-step link forecasting · Yelp | Micro-AUC: 70.21 ± 0.1 -> 81.38 ± 0.2 | Helped |
| Use NLSM instead of the strongest listed baseline | Single-step link forecasting · ML-10M | Micro-AUC: 90.82 ± 0.3 -> 92.21 ± 0.4 | Helped |
| Use NLSM instead of the strongest listed baseline | Single-step link forecasting · ML-10M | Macro-AUC: 93.68 ± 0.1 -> 92.39 ± 0.3 | Hurt |
| Use relation-specific interaction matrices and NLSM inference | Temporal KG link forecasting · WIKI filtered | MRR: 53.57 -> 56.70 | Helped |
| Use relation-specific interaction matrices and NLSM inference | Temporal KG link forecasting · WIKI raw | MRR: 32.44 -> 35.25 | Helped |
| Use relation-specific interaction matrices and NLSM inference | Temporal KG link forecasting · YAGO filtered | MRR: 66.80 -> 69.40 | Helped |
| Use relation-specific interaction matrices and NLSM inference | Temporal KG link forecasting · YAGO raw | MRR: 48.60 -> 52.50 | Helped |
| Replace GRU-based posterior inference with independent per-time-step variational parameters | NLSM single-step link forecasting · Communication and rating networks | Micro-AUC | Hurt |
| Increase latent dimension K | NLSM single-step link forecasting · Appendix F datasets | Macro-AUC | Hurt |
| Apply the slowly changing network assumption to a rapidly changing contact network | NLSM · Infocom | AUC: 0.804 -> 0821 ± 0.007 | Hurt |
Closest papers by meaning
- State Space Models on Temporal Graphs: A First-Principles Study (NeurIPS 2024 · similarity 0.87)
- A Graph Dynamics Prior for Relational Inference (AAAI 2024 · similarity 0.87)
- Continuous-Time Graph Representation with Sequential Survival Process (AAAI 2024 · similarity 0.86)
- TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction (NeurIPS 2025 · similarity 0.86)
- Simple and Efficient Heterogeneous Temporal Graph Neural Network (NeurIPS 2025 · similarity 0.86)
- Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis (AAAI 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.