Research map / Label-efficient and robust learning / Recognition and long-tail
Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
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 the proposed hyperbolic embedding with self-guided random walks instead of HHNE | Heterogeneous network embedding · DBLP and MovieLens network reconstruction and link prediction | AUC: 0.8803 vs 0.8777 (DBLP P-A link prediction, dimension 2); 0.8498 vs 0.7715 (MovieLens M-A link prediction, dimension 2) | Helped |
| Use the proposed method rather than HHNE for 2-dimensional DBLP P-A network reconstruction | Heterogeneous network embedding · DBLP network reconstruction P-A, dimension 2 | AUC: 0.9835 vs 0.9602 | Hurt |
| Use the proposed method rather than HHNE for 2-dimensional MovieLens M-D network reconstruction | Heterogeneous network embedding · MovieLens network reconstruction M-D, dimension 2 | AUC: 0.9952 vs 0.9904 | Hurt |
| Increase embedding dimension from 2 to 25 | Our method · DBLP and MovieLens reconstruction and link prediction | AUC: 0.9602 -> 0.9986 (DBLP reconstruction P-A); 0.8498 -> 0.8765 (MovieLens link prediction M-A) | Helped |
| Vary model hyperparameters | Our method · MovieLens link prediction | AUC | No clear effect |
| Set context size below 5 | Our method · MovieLens link prediction | AUC | Hurt |
| Set random-walk length below 10 | Our method · MovieLens link prediction | AUC | Hurt |
| Use longer random walks | Self-guided random walk · MovieLens link prediction | AUC | Helped |
Closest papers by meaning
- Hyperbolic Heterogeneous Information Network Embedding (AAAI 2019 · similarity 0.91)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.88)
- Conditional Network Embeddings (ICLR 2019 · similarity 0.88)
- Non-Euclidean Mixture Model for Social Network Embedding (NeurIPS 2024 · similarity 0.87)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.87)
- Link Prediction in Multilayer Networks via Cross-Network Embedding (AAAI 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.