Research map / Graph learning / Graph algorithms and clustering
SepNE: Bringing Separability to Network Embedding
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 SepNE instead of DeepWalk | Network embedding · Wiki, 10% train | micro-averaged F1: 0.5737 -> 0.5764 | Helped |
| Use SepNE instead of DeepWalk | Network embedding · Wiki, 90% train | micro-averaged F1: 0.6893 -> 0.6867 | Hurt |
| Use SepNE instead of DeepWalk | Network embedding · Cora, 10% train | micro-averaged F1: 0.7509 -> 0.7365 | Hurt |
| Use SepNE instead of DeepWalk | Network embedding · Cora, 90% train | micro-averaged F1: 0.8187 -> 0.8220 | Helped |
| Use SepNE instead of DeepWalk | Network embedding · Citeseer | micro-averaged F1: 0.5086 -> 0.5157; 0.5813 -> 0.6072 | Helped |
| Use SepNE-LP instead of DeepWalk | Flickr multi-label prediction · Flickr, 10% train | micro-averaged F1: 0.4481 -> 0.4623 | Helped |
| Use SepNE-LP instead of DeepWalk | Flickr multi-label prediction · Flickr, 90% train | micro-averaged F1: 0.4592 -> 0.4677 | Helped |
| Use SepNE-LP instead of DeepWalk | Youtube multi-label prediction · Youtube | micro-averaged F1: 1% train: 0.2037 -> 0.2253; 90% train: 0.4556 -> 0.4277 | Mixed |
| Use Louvain community partitions instead of random partitions (ablation) | SepNE · Flickr | micro-averaged F1: 0.4601 -> 0.4623 (10% train); 0.4658 -> 0.4677 (90% train) | Helped |
| Use Louvain community partitions instead of random partitions (ablation) | SepNE · Youtube | micro-averaged F1: 0.3355 -> 0.3361 (3% train); 0.4273 -> 0.4277 (90% train) | Mixed |
| Increase the global-loss weight lambda (ablation) | SepNE on Flickr · Flickr | micro-averaged F1 | Helped |
| Vary iteration count, landmark count, or regularization eta (ablation) | SepNE on Flickr · Flickr | micro-averaged F1 | No clear effect |
Closest papers by meaning
- Community Preserving Network Embedding (AAAI 2017 · similarity 0.89)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.87)
- Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (ICLR 2018 · similarity 0.87)
- DepthLGP: Learning Embeddings of Out-of-Sample Nodes in Dynamic Networks (AAAI 2018 · similarity 0.87)
- Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning (NeurIPS 2025 · similarity 0.87)
- 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.