Research map / Probabilistic and scientific modeling / Variational and generative sampling
Consistent Nonparametric Methods for Network Assisted Covariate Estimation
Xueyu Mao, Deepayan Chakrabarti, Purnamrita Sarkar
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 CN-VEC instead of node2vec/NOBE embeddings for covariate prediction | CN-VEC · SBM timing (Figure 3) | wall-clock time: 10x-100x faster | Improved |
| vary number of nearest neighbors k in CN-VEC | CN-VEC · simulated SBM | RMSE: sweet spot k in [10, 20] | Mixed |
| use CN-VEC (2-hop neighborhood row similarity) instead of SVD-RBF | CN-VEC · LSM, SBM, RDPG simulations | RMSE | Improved |
| use CN-VEC instead of SVD-RBF on MMSB | CN-VEC · MMSB simulation | RMSE | No clear effect |
| use SVD-RBF on a full-rank latent space model | SVD-RBF · LSM simulation | RMSE | Hurt |
| use SVD-RBF when P need not be low-rank (clipped link probabilities) | SVD-RBF · RDPG simulation | RMSE | Hurt |
| use SVD-RBF on Sinanet instead of Cora/CiteSeer | SVD-RBF · Sinanet | RMSE | Hurt |
| use CN-VEC versus node2vec and NOBE in accuracy | CN-VEC · Cora, CiteSeer, Sinanet | RMSE | No clear effect |
| use common neighbor counts instead of adjacency matrix as similarity (ablation) | nearest-neighbor regression · simulated and real networks | RMSE | Improved |
| use personalized PageRank instead of common neighbors as similarity (ablation) | nearest-neighbor regression · Cora, CiteSeer | RMSE | Improved |
| use CN/Jaccard instead of W-PPR as similarity (ablation) | nearest-neighbor regression · Sinanet | RMSE | Improved |
| use Jaccard instead of raw common neighbor counts (ablation) | nearest-neighbor regression · all datasets | RMSE | No clear effect |
Closest papers by meaning
- Node Regression on Latent Position Random Graphs via Local Averaging (JMLR 2026 · similarity 0.88)
- Universal Latent Space Model Fitting for Large Networks with Edge Covariates (JMLR 2020 · similarity 0.87)
- High-dimensional Gaussian graphical models on network-linked data (JMLR 2020 · similarity 0.86)
- Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation (AAAI 2016 · similarity 0.86)
- On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models (ICML 2026 · similarity 0.85)
- Logistic Regression Under Network Dependence (JMLR 2024 · 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.
