Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
A Bayesian Take on Gaussian Process Networks
Enrico Giudice, Jack Kuipers, Giusi Moffa
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 GP score with MCMC sampling instead of BGe score | partition/order MCMC · non-linear synthetic data (lambda=1) | E-SHD | Improved |
| use GP score instead of BGe score on linear data | partition/order MCMC · synthetic data lambda=0 and 0.5 | E-SHD | No clear effect |
| reweight Laplace-approximation samples by importance sampling with bridge-sampled scores (ablation) | GP partition MCMC · 4-node DAG posterior | reverse K-L divergence | Improved |
| use GP partition MCMC instead of DiBS+ for posterior estimation | GP partition MCMC · 4-node DAG posterior | reverse K-L divergence: 27.8 | Improved |
| add first-order interactions to additive kernel (GP^2) (ablation) | GP partition · flow cytometry | E-SHD: 14.5 -> 16.7 | Hurt |
| add first-order interactions to additive kernel (GP^2) (ablation) | GP order · flow cytometry | E-SHD: 14.6 -> 16.7 | Hurt |
| add first-order interactions to additive kernel (GP^2) (ablation) | GP partition · flow cytometry | P(no Erk -> PKA): 0.75 -> 0 | Hurt |
| use GP score instead of BGe score (partition) | partition MCMC · flow cytometry | P(Erk -> Akt): 0 -> 1 | Improved |
| use GP score instead of BGe score (partition) | partition MCMC · flow cytometry | P(no Erk -> PKA): 1 -> 0.75 | Hurt |
| use GP score instead of BGe score (partition) | partition MCMC · flow cytometry | E-SHD: 15.9 -> 14.5 | Improved |
| use GP score instead of BGe score (partition) | partition MCMC · flow cytometry | E-TP: 4.3 -> 7.2 | Improved |
| use order MCMC instead of partition MCMC (ablation) | GP score · flow cytometry | P(no Erk -> PKA): 0.75 -> 0.42 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DiBS+ — DIBS: Diversity Inducing Information Bottleneck in Model Ensembles (AAAI 2021) · better on 4 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network (NeurIPS 2023 · similarity 0.87)
- Scalable Deep Gaussian Markov Random Fields for General Graphs (ICML 2022 · similarity 0.87)
- Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning (ICLR 2023 · similarity 0.87)
- Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project (NeurIPS 2025 · similarity 0.86)
- Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations (NeurIPS 2025 · similarity 0.86)
- Conditioning Gaussian Processes on Almost Anything (NeurIPS 2026 · 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.
