Research map / Graph learning / Graph self-supervised learning
Network Structure and Transfer Behaviors Embedding via Deep Prediction Model
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 |
|---|---|---|---|
| DNE embeddings instead of DeepWalk | node classification · Cora 10% labeled | accuracy (%): 71.77 -> 71.86 | No clear effect |
| DNE instead of DeepWalk | node classification · Citeseer 90% labeled | accuracy (%): 59.42 -> 61.56 | Helped |
| DNE instead of DeepWalk | node classification · Pubmed 10% labeled | accuracy (%): 70.75 -> 73.74 | Helped |
| DNE instead of best baseline | clustering · 20-Newsgroups 9-NG | NMI: 0.254 -> 0.425 | Helped |
| LSTM-based DNE instead of Skip-Gram DeepWalk | multilabel classification · BlogCatalog | Micro-F1 (%): 42.00 -> 42.13 at 90% | Mixed |
| use degree-weight biased random walk instead of truncated or biased random walk (ablation) | DNE · BlogCatalog | Micro-F1 | Helped |
| increase walks per node (ablation) | DNE · Cora | accuracy | Helped |
| increase walk length (ablation) | DNE · Cora | accuracy | No clear effect |
Closest papers by meaning
- DepthLGP: Learning Embeddings of Out-of-Sample Nodes in Dynamic Networks (AAAI 2018 · similarity 0.89)
- Temporal Network Embedding with High-Order Nonlinear Information (AAAI 2020 · similarity 0.88)
- Transfer Learning for Deep Learning on Graph-Structured Data (AAAI 2017 · similarity 0.88)
- Watch Your Step: Learning Node Embeddings via Graph Attention (NeurIPS 2018 · similarity 0.88)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.87)
- Community Detection Guarantees using Embeddings Learned by Node2Vec (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.