Research map / Graph learning / Graph self-supervised learning
Deep Amortized Relational Model with Group-Wise Hierarchical Generative Process
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 DaRM's group-wise hierarchical generative process instead of the strongest baseline | Relational community detection and link prediction · NIPS12, Cora, CiteSeer, and Pubmed | ACC, NMI, and AUC | Helped |
| Use DaRM's group-wise hierarchical generative process instead of the strongest baseline | Relational community detection · NIPS12, Cora, CiteSeer, and Pubmed | DBI | Helped |
| Vary the number of selected pioneer nodes; about 5 works best on NIPS12, CiteSeer, and Pubmed, and 3 on Cora (ablation) | DaRM · NIPS12, Cora, CiteSeer, and Pubmed | ACC | Mixed |
| Increase the graph-embedding layer count L (ablation) | DaRM · NIPS12, Cora, CiteSeer, and Pubmed | ACC | Helped |
| Increase the graph-embedding layer count L (ablation) | DaRM · NIPS12, Cora, CiteSeer, and Pubmed | running time | Hurt |
Closest papers by meaning
- Deep Generative Models for Relational Data with Side Information (ICML 2017 · similarity 0.90)
- HiGen: Hierarchical Graph Generative Networks (ICLR 2024 · similarity 0.86)
- Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective (ICML 2024 · similarity 0.84)
- Deep Representation Learning for Forecasting Recursive and Multi-Relational Events in Temporal Networks (AAAI 2025 · similarity 0.83)
- RelGNN: Composite Message Passing for Relational Deep Learning (ICML 2025 · similarity 0.83)
- Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis (AAAI 2024 · similarity 0.83)
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.