Research map / Label-efficient and robust learning / Recognition and long-tail
Structural Deep Embedding for Hyper-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 |
|---|---|---|---|
| Use DHNE instead of the strongest reported baseline | Hyper-network embedding · GPS network reconstruction | AUC: 0.9337 -> 0.9598 | Helped |
| Use DHNE instead of the strongest reported baseline | Hyper-network embedding · MovieLens network reconstruction | AUC: 0.9142 -> 0.9344 | Helped |
| Use DHNE instead of the strongest reported baseline | Hyper-network embedding · drug network reconstruction | AUC: 0.8236 -> 0.9356 | Helped |
| Use DHNE instead of the strongest reported baseline | Hyper-network embedding · wordnet network reconstruction | AUC: 0.8609 -> 0.9073 | Helped |
| Use DHNE instead of the strongest reported baseline | Hyper-network embedding · GPS link prediction | AUC: 0.8687 -> 0.9166 | Helped |
| Use DHNE instead of the strongest reported baseline | Hyper-network embedding · MovieLens link prediction | AUC: 0.8211 -> 0.8676 | Helped |
| Use DHNE instead of the strongest reported baseline | Hyper-network embedding · drug link prediction | AUC: 0.8191 -> 0.9254 | Helped |
| Use DHNE instead of the strongest reported baseline | Hyper-network embedding · wordnet link prediction | AUC: 0.8003 -> 0.8268 | Helped |
| Add second-order proximity reconstruction to first-order-only DHNE (ablation) | DHNE on drug link prediction · drug | AUC | Helped |
| Increase the second-order loss weight from the reported best range to α = 5 (ablation) | DHNE on drug link prediction · drug | AUC | Hurt |
| Increase embedding dimension beyond 32 (ablation) | DHNE on drug link prediction · drug | AUC | No clear effect |
Closest papers by meaning
- Conditional Network Embeddings (ICLR 2019 · similarity 0.88)
- Defining and Discovering Hyper-meta-paths for Heterogeneous Hypergraphs (NeurIPS 2025 · similarity 0.88)
- Hyperbolic Heterogeneous Information Network Embedding (AAAI 2019 · similarity 0.87)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.86)
- Hypergraph Joint Representation Learning for Hypervertices and Hyperedges via Cross Expansion (AAAI 2024 · similarity 0.86)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 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.