Research map / Graph learning / GNN architectures
Ensemble Learning for Relational Data
Hoda Eldardiry, Jennifer Neville, Ryan A. Rossi
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 |
|---|---|---|---|
| use CEC (interleaved inference) instead of independent RE inference (ablation) | RE ensemble · Synthetic multi-source (high autocorrelation) | AUC: 0.64 -> 0.74 | Improved |
| use CEC instead of RE at high linkage (ablation) | RE ensemble · Synthetic multi-source (high linkage) | AUC: 0.73 -> 0.82 | Improved |
| use CEC instead of RE at low autocorrelation (ablation) | RE ensemble · Synthetic multi-source (low autocorrelation) | AUC: 0.53 -> 0.55 | Improved |
| use RE ensemble instead of multiple-relation single model MR (ablation) | MR single model · Synthetic multi-source (high linkage) | AUC: 0.68 -> 0.73 | Improved |
| add CEC interleaved inference with RSR resampling versus IID-RE (ablation) | IID-RE · Synthetic and Facebook single graph | AUC | Improved |
| use RSR resampling instead of IID resampling with RE inference (ablation) | IID-RE · Synthetic and Facebook single graph | AUC | Improved |
| use CEC inference instead of RE with IID resampling (ablation) | IID-RE · Synthetic and Facebook single graph | AUC | Improved |
| use ensemble instead of single model (ablation) | SM single model · Synthetic and Facebook single graph | AUC | Improved |
| add more link sources to the ensemble | CEC · Synthetic multi-source (1 to 9 sources) | AUC | Improved |
| add more link sources to single-model baselines MR and CR | MR, CR · Synthetic multi-source (1 to 9 sources) | AUC | Hurt |
| interleave more models during inference (hybrid from RE to CEC) (ablation) | RE with 10 link sources · Synthetic multi-source (10 sources) | AUC | Improved |
| use CEC when few test labels are available | RE · Facebook and IMDb multi-source | AUC | Improved |
Closest papers by meaning
- Enhancing Ensemble Clustering with Adaptive High-Order Topological Weights (AAAI 2024 · similarity 0.85)
- Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models (NeurIPS 2025 · similarity 0.85)
- Core Knowledge Learning Framework for Graph (AAAI 2025 · similarity 0.84)
- From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble (ICML 2024 · similarity 0.84)
- Fully-inductive Node Classification on Arbitrary Graphs (ICLR 2025 · similarity 0.84)
- Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective (ICML 2024 · 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.
