Research map / Graph learning / Knowledge and temporal graphs
Variational Graph Recurrent Neural Networks
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 latent random variables to GRNN (VGRNN) (ablation) | GRNN · COLAB link detection | AUC: 86.40 -> 88.67 | Helped |
| add latent random variables to GRNN (VGRNN) (ablation) | GRNN · Social Evo. link detection | AUC: 78.27 -> 82.69 | Helped |
| add latent random variables to GRNN (VGRNN) (ablation) | GRNN · Cora link detection | AUC: 91.35 -> 92.08 | Helped |
| semi-implicit posterior (SI-VGRNN vs VGRNN) (ablation) | VGRNN · Cora link detection | AUC: 92.08 -> 94.07 | Helped |
| semi-implicit posterior (SI-VGRNN vs VGRNN) (ablation) | VGRNN · Facebook link detection | AUC: 88.00 -> 88.12 | No clear effect |
| semi-implicit posterior (SI-VGRNN vs VGRNN) (ablation) | VGRNN · dynamic link prediction | AUC: COLAB 85.95 -> 85.45; Facebook 89.47 -> 90.94 | Mixed |
| model temporal dependencies (VGRNN vs static VGAE) | VGAE · Enron link detection | AUC: 88.26 -> 94.41 | Helped |
| VGRNN vs DynAERNN | dynamic graph embedding · Facebook link prediction | AUC: 76.02 -> 89.47 | Helped |
| VGRNN vs DynAERNN | dynamic graph embedding · Facebook new link prediction | AUC: 76.35 -> 87.20 | Helped |
| VGRNN vs DynAERNN | dynamic graph embedding · Enron link prediction | AUC: 87.43 -> 93.10 | Helped |
Closest papers by meaning
- Towards Dynamic Message Passing on Graphs (NeurIPS 2024 · similarity 0.88)
- Valid Conformal Prediction for Dynamic GNNs (ICLR 2025 · similarity 0.88)
- When Graph Neural Networks Meet Dynamic Mode Decomposition (ICLR 2025 · similarity 0.88)
- Learning Latent Graph Structures and their Uncertainty (ICML 2025 · similarity 0.87)
- Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks (NeurIPS 2024 · similarity 0.87)
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · similarity 0.87)
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.