Research map / Learning theory and algorithms / Sample complexity
Recovering shared structure from multiple networks with unknown edge distributions
Keith Levin, Asad Lodhia, Elizaveta Levina
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 estimated-variance weighted averaging instead of unweighted averaging of networks | low-rank eigenvalue truncation estimate of P · Simulation with one outlier-variance network (Laplace noise, n=200, 50 trials) | relative improvement in Frobenius error: relative improvement never negative; large for single high-variance outlier | Improved |
| switch from unweighted to weighted network averaging | K-means clustering of COBRE brain networks · COBRE fMRI | fraction of vertices assigned to different communities: between ten and forty percent of vertices change cluster | Mixed |
| switch from unweighted to weighted network averaging | cell-level two-sample t-tests, schizophrenia vs healthy · COBRE fMRI, Benjamini-Hochberg FDR 0.01 | number of rejected cells: seven additional cells rejected; strict superset of unweighted rejections | Improved |
| switch from Benjamini-Hochberg to Benjamini-Yekutieli correction | weighted vs unweighted cell tests · COBRE fMRI | which procedure rejects a superset: unweighted procedure rejects a superset of the weighted procedure's cells | Mixed |
Closest papers by meaning
- Learning Interpretable Models for Coupled Networks Under Domain Constraints (AAAI 2021 · similarity 0.89)
- Bayesian Spiked Laplacian Graphs (JMLR 2023 · similarity 0.87)
- When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors (NeurIPS 2026 · similarity 0.87)
- Inference for Multiple Heterogeneous Networks with a Common Invariant Subspace (JMLR 2021 · similarity 0.87)
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation (NeurIPS 2026 · similarity 0.86)
- Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models (NeurIPS 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.
