Research map / Learning theory and algorithms / Matrix and tensor methods
Node Embeddings and Exact Low-Rank Representations of Complex 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 |
|---|---|---|---|
| Optimize reconstruction loss on the thresholded adjacency using logistic PCA rather than the unthresholded low-rank approximation | Node embeddings · 100-triangle cycle toy graph | relative Frobenius error: 0.894 -> 0.031 | Helped |
| Use TSVD instead of LPCA for reconstruction | Node embeddings · Real-world networks | low-degree triangle recovery | Hurt |
| Use rank 16 LPCA instead of rank 112 TSVD | BlogCatalog embeddings · BlogCatalog | relative Frobenius error: $.82 vs. $.73 | Hurt |
| Use rank 16 LPCA instead of rank 112 or 128 TSVD | BlogCatalog embeddings · BlogCatalog | low-degree triangle recovery | Helped |
| Increase LPCA embedding rank (ablation) | LPCA · Real-world networks | degree and participating-triangle sequence reconstruction | Helped |
| Use TSVD rather than LPCA for embeddings | Node embeddings · Real-world networks | degree and participating-triangle sequence reconstruction | Hurt |
| Fit LPCA at the exact factorization dimension (ablation) | LPCA · Real-world networks | exact adjacency reconstruction | Helped |
| Replace a real network with a random graph having the same expected degree sequence | LPCA factorization · Real-world networks | exact factorization dimension | Hurt |
Closest papers by meaning
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.91)
- On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models (ICML 2026 · similarity 0.88)
- Community Detection Guarantees using Embeddings Learned by Node2Vec (NeurIPS 2024 · similarity 0.87)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.87)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.86)
- Information Loss and Disparate Effects in Network Embeddings (NeurIPS 2026 · similarity 0.85)
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.