Research map / Probabilistic and scientific modeling / Variational and generative sampling
Bayesian inference on random simple graphs with power law degree distributions
Juho Lee, Creighton Heaukulani, Zoubin Ghahramani, Lancelot F. James, Seungjin Choi
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 BFRY rather than Gamma weights | Generalized random graph · Simulated graphs, true α=0.3, 0.5, and 0.7 | max test log-likelihood: BFRY: -57323.19 ± 91.62, -21077.62 ± 79.64, -7894.67 ± 41.84; Gamma: -71341.90 ± 116.82, -24430.38 ± 73.06, -8511.48 ± 2 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · Simulated graphs, true α=0.3, 0.5, and 0.7 | avg test log-likelihood: BFRY: -57675.72 ± 31.71, -21289.75 ± 34.23, -8027.42 ± 51.08; Gamma: -71841.66 ± 47.38, -24701.06 ± 11.31, -8601.50 ± 15 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · 500Air | max test log-likelihood: -1842.10 ± 3.97 -> -1628.51 ± 10.46 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · 500Air | avg test log-likelihood: -1870.35 ± 0.28 -> -1654.20 ± 6.79 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · polblogs | max test log-likelihood: -555.24 ± 18.27 -> -474.67 ± 32.20 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · polblogs | avg test log-likelihood: -596.78 ± 0.78 -> -503.20 ± 37.85 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · Fb107 | max test log-likelihood: -18403.66 ± 31.76 -> -18098.38 ± 20.50 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · Fb107 | avg test log-likelihood: -18568.05 ± 2.79 -> -18209.94 ± 12.86 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · openfl | max test log-likelihood: -17475.52 ± 31.97 -> -16561.13 ± 137.89 | Improved |
| Use BFRY rather than Gamma weights | Generalized random graph · openfl | avg test log-likelihood: -17746.79 ± 6.65 -> -16947.70 ± 177.21 | Improved |
Closest papers by meaning
- Statistical Inference of Random Graphs With a Surrogate Likelihood Function (JMLR 2025 · similarity 0.88)
- Probabilistic Circuits for Variational Inference in Discrete Graphical Models (NeurIPS 2020 · similarity 0.88)
- Simultaneous Inference for Pairwise Graphical Models with Generalized Score Matching (JMLR 2020 · similarity 0.87)
- Learning Non-Gaussian Graphical Models via Hessian Scores and Triangular Transport (JMLR 2024 · similarity 0.87)
- Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models (NeurIPS 2026 · similarity 0.86)
- Total Variation Distance Meets Probabilistic Inference (ICML 2024 · similarity 0.86)
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.
