Research map / Graph learning / Graph self-supervised learning
Graph-Conditional Flow Matching for Relational Data Generation
Davide Scassola, Sebastiano Saccani, Luca Bortolussi
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 GNN node embeddings to the denoiser (ablation) | graph-conditional flow matching · AirBnB, Biodegradability, IMDB, Rossmann, Walmart | XGBoost discriminator accuracy: 0.70 -> 0.58 (AirBnB); 0.86 -> 0.59 (Biodegradability); 0.89 -> 0.59 (IMDB) | Improved |
| add GNN node embeddings to the denoiser (ablation) | graph-conditional flow matching · CORA | XGBoost discriminator accuracy: 0.62 -> 0.63 | No clear effect |
| flow matching with GNN vs latent diffusion of Hudovernik (2024) | graph-conditional flow matching · Walmart | XGBoost discriminator accuracy: 0.79 -> 0.73 | Improved |
| flow matching with GNN vs ClavaDDPM | graph-conditional flow matching · IMDB MovieLens | XGBoost discriminator accuracy: 0.83 -> 0.59 | Improved |
| flow matching with GNN vs Hudovernik (2024) | graph-conditional flow matching · CORA | XGBoost discriminator accuracy: 0.60 -> 0.63 | Hurt |
| remove duplicated child records after generation | graph-conditional flow matching · CORA | XGBoost discriminator accuracy: 0.63 -> ≈0.50 | Improved |
Closest papers by meaning
- Joint Relational Database Generation via Graph-Conditional Diffusion Models (NeurIPS 2025 · similarity 0.91)
- ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models (NeurIPS 2024 · similarity 0.87)
- DeFoG: Discrete Flow Matching for Graph Generation (ICML 2025 · similarity 0.86)
- Position: Relational Deep Learning - Graph Representation Learning on Relational Databases (ICML 2024 · similarity 0.86)
- WikiDBs: A Large-Scale Corpus Of Relational Databases From Wikidata (NeurIPS 2024 · similarity 0.84)
- Breaking the Quality–Privacy Tradeoff in Tabular Data Generation via In-Context Learning (NeurIPS 2026 · similarity 0.84)
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.
