Research map / Graph learning / GNN architectures
Quantifying Network Similarity using Graph Cumulants
Gecia Bravo-Hermsdorff, Lee M. Gunderson, Pierre-André Maugis, Carey E. Priebe
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 graph cumulants instead of graph moments as test statistics | two-sample graph test · Synthetic two-by-two SBMs (n=128, n=256) | AUC | Improved |
| use graph cumulants instead of graph moments as test statistics | two-sample graph test · FunCoup gene networks (Mouse, Rat, Human, Arabidopsis) | discrimination power | Improved |
| use cumulants so tests work with a single graph per sample | two-sample graph test · Synthetic SBMs (single graph per sample) | AUC | Improved |
| use cumulants for false-positive control (chi-square calibration) | squared Mahalanobis distance test · Same-distribution sample pairs | distribution of squared Mahalanobis distance | Improved |
Closest papers by meaning
- High-dimensional Gaussian graphical models on network-linked data (JMLR 2020 · similarity 0.88)
- On the Propagation of Low-Rate Measurement Error to Subgraph Counts in Large Networks (JMLR 2017 · similarity 0.86)
- Network two-sample test for block models (NeurIPS 2025 · similarity 0.86)
- TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs (NeurIPS 2024 · similarity 0.85)
- Sample Complexity of Correlation Detection in the Gaussian Wigner Model (ICML 2025 · similarity 0.84)
- Harnessing Multiple Correlated Networks for Exact Community Recovery (NeurIPS 2024 · similarity 0.84)
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.
