Research map / Probabilistic and scientific modeling / Variational and generative sampling
Universal Latent Space Model Fitting for Large Networks with Edge Covariates
Zhuang Ma, Zongming Ma, Hongsong Yuan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 LSCD (latent space fit + K-means) instead of SCORE | LSCD · Simmons College | mis-clustered proportion: 23.57% -> 11.87% | Improved |
| use LSCD instead of SCORE | LSCD · Caltech | mis-clustered proportion: 30.34% -> 18.14% | Improved |
| use LSCD instead of CMM (third best) | LSCD · Caltech | mis-clustered proportion: 21.02% -> 18.14% | Improved |
| use LSCD instead of SCORE | LSCD · Political Blog | mis-clustered proportion: 4.746% -> 4.910% | No clear effect |
| use Latentnet instead of LSCD | Latentnet · Political Blog | mis-clustered proportion: 4.910% -> 4.513% | Improved |
| increase dimension from K to K+1 (ablation) | SCORE · Political Blog | mis-clustered proportion: 4.746% -> 23.159% | Hurt |
| increase dimension from K to K+1 (ablation) | SCORE · Simmons College | mis-clustered proportion: 23.57% -> 16.45% | Improved |
| increase dimension from K to K+1 (ablation) | LSCD · Simmons College | mis-clustered proportion: 11.87% -> 11.17% | No clear effect |
| increase dimension from K to K+1 (ablation) | LSCD · Caltech | mis-clustered proportion: 18.14% -> 20.17% | No clear effect |
| add covariate (same practice indicator) to latent space model (ablation) | LSCD · Lawyer network | number of mis-clustered nodes: 12 errors, reduced by 50% | Improved |
| use different initialization (convex, SVT, random) for the non-convex algorithm (ablation) | Algorithm 1 · simulation n=4000, k=4 | relative estimation error | No clear effect |
| increase network size under a general kernel model (ablation) | Algorithm 1 · simulation, general kernel | optimal fitting dimension: optimal k increases with n | Improved |
Closest papers by meaning
- A Flexible Latent Space Model for Multilayer Networks (ICML 2020 · similarity 0.90)
- Latent Space Inference of Internet-Scale Networks (JMLR 2016 · similarity 0.88)
- Maximum Likelihood Embedding of Logistic Random Dot Product Graphs (AAAI 2020 · similarity 0.88)
- Consistent Nonparametric Methods for Network Assisted Covariate Estimation (ICML 2021 · similarity 0.87)
- On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models (ICML 2026 · similarity 0.87)
- GLAD: Improving Latent Graph Generative Modeling with Simple Quantization (AAAI 2025 · 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.
